SlideShare a Scribd company logo
1 of 48
Learning item and user representations with sparse data in recommender systems
Ed H. Chi
Google Inc.
Abstract:
Recommenders match users in a particular context with the best personalized items that they will engage with. The problem is that users have shifting item and
topic preferences, and give sparse feedback over time (or no-feedback at all). Contexts shift from interaction-to-interaction at various time scales (seconds to
minutes to days). Learning about users and items is hard because of noisy and sparse labels, and the user/item set changes rapidly and is large and long-tailed.
Given the enormity of the problem, it is a wonder that we learn anything at all about our items and users.
In this talk, I will outline some research at Google to tackle the sparsity problem. First, I will summarize some work on focused learning, which suggests that
learning about subsets of the data requires tuning the parameters for estimating the missing unobserved entries. Second, we utilize joint feature factorization to
impute possible user affinity to freshly-uploaded items, and employ hashing-based techniques to perform extremely fast similarity scoring on a large item
catalog, while controlling variance. This approach is currently serving a ~1TB model on production traffic using distributed TensorFlow Serving, demonstrating that
our techniques work in practice. I will conclude with some remarks on possible future directions.
Bio:
Ed is a Research Scientist at Google, leading a team focused on recommendation systems, machine learning, and social interaction research. He has launched
significant improvements of recommenders for YouTube, Google Play Store and Google+. With over 35 patents and over 100 research articles, he is known for
research on Web and online social systems, and the effects of social signals on user behavior. Prior to Google, he was the Area Manager and Principal Scientist at
Palo Alto Research Center‘s Augmented Social Cognition Group, where he led the group in understanding how social systems help groups of people to
remember, think and reason. Ed completed his three degrees (B.S., M.S., and Ph.D.) in 6.5 years from University of Minnesota, and has been doing research on
software systems since 1993. He has been featured and quoted in the press, including the Economist, Time Magazine, LA Times, and the Associated Press, and
has won awards for both teaching and research. In his spare time, Ed is an avid photographer and snowboarder.
1
Confidential + Proprietary
Ed H. Chi
Research Scientist & Manager, MLX/SIR Research team
Google Research & Machine Intelligence
Learning Item and User Representations with
Sparse Data in Recommender Systems
Confidential & Proprietary 3
TFXan end-to-end
ML platform based on
TensorFlow.
Confidential & Proprietary
John Riedl (1962-2013)
(wikipedia)
4
Confidential & Proprietary
The Recommendation Problem
User Context Item
5
Confidential & Proprietary
f( , ) ≈
The Recommendation Problem
User Context Item
6
Confidential & Proprietary
The Recommendation Problem
User Context Item
Watch
History
Source
Preferences
Demographics Client Last
Interaction
Leanback or
Lean-forward
Topic Past user
behavior
Clickbait /
Brand safe?
7
Confidential & Proprietary
The Recommendation Problem
User Context Item
Shifting User
Preferences;
Sparse Feedback
8
Confidential & Proprietary
The Recommendation Problem
User Context Item
Shifting User
Preferences;
Sparse Feedback
Dynamic and
Changing
Contexts
9
Confidential & Proprietary
The Recommendation Problem
User Context Item
Noisy & Sparse
Labels;
Large Changing
Item Set
Shifting User
Preferences;
Sparse Feedback
Dynamic and
Changing
Contexts
10
Confidential & Proprietary
The Recommendation Problem
User Context Item
Noisy & Sparse
Labels;
Large Changing
Item Set
Shifting User
Preferences;
Sparse Feedback
Dynamic and
Changing
Contexts
Oh, and do this with low latency
with a huge corpus of users and items!
11
Confidential & Proprietary
2 Stories
1. Focused Learning for the Long-Tail
2. Factorized Deep Retrieval
12
Confidential & Proprietary
The Recommendation Problem
5
3
1
2
1
5
4
3
Users
Items
13
Confidential & Proprietary
The Recommendation Problem
Given: Observed (user, item) ratings
Find: A model that predicts the missing
ratings well5
3
1
2
1
5
4
3
?
?
?
?
?
?
?
?
Users
Items
14
Confidential & Proprietary
Recommender quality inconsistent across movies
Error (RMSE)
Genre 15
Confidential & Proprietary
Skewed Data
“Globally optimal” = Tyranny of the Majority
16
Confidential & Proprietary
We don’t represent users/items equally!
Per-User Prediction Accuracy
Frequency
Error (MSE)
Per-Movie Prediction Accuracy
Frequency
Error (MSE)
Wanted: A model that predicts well
for all users and all items.
17
Confidential & Proprietary
Focused Learning Problem Definition
Given:
● A dataset: R
● Group of items (or users) to focus on: I
Find: A model that has high prediction accuracy for RI
18
Confidential & Proprietary
Approach
1. Focus Selection - Where should the additional models focus?
2. Focused Learning - How can learn a new model to improve
prediction on a subset of the data?
19
Confidential & Proprietary
Approach
1. Focus Selection - Where should the additional models focus?
2. Focused Learning - How can learn a new model to improve
prediction on a subset of the data?Subset of columns
Movies
Users
Movies
Users
Subset of rows
“Focus Group” 20
Confidential & Proprietary
Approach
1. Focus Selection - Where should the additional models focus?
2. Focused Learning - How can learn a new model to improve
prediction on a subset of the data?
21
Confidential & Proprietary
High-Level Approach
(1) Learn model
(2) Return accuracy on validation set.
22
Confidential & Proprietary
Focused Hyperparameter Optimization
Typical
Hyperparameter
Optimization
(1) Learn model
(2) Return accuracy on validation set.
23
Confidential & Proprietary
Focused Hyperparameter Optimization
Typical
Hyperparameter
Optimization
Focused
Hyperparameter
Optimization
(1) Learn matrix factorization model
(2) Return accuracy on validation set.
Choose model based on focused group!
24
Confidential & Proprietary
An Example of Focused Learning
Allow for different regularization
for focus group and “unfocus” group
25
Confidential & Proprietary
Focus by Genre
26
Confidential & Proprietary
Focus on Cold-Start Movies
27
Confidential & Proprietary
Summary
1. “Globally optimal” is not best for
everybody.
Myth of the average user!
2. Learn additional models focused
on problematic regions.
The long-tail needs different
exploration strategies!
Per-User Prediction Accuracy
Frequency
MSE
Alex Beutel, Ed H. Chi, Zhiyuan Cheng, Hubert Pham, John
Anderson. Beyond Globally Optimal: Focused Learning
for Improved Recommendations. In WWW 2017.
28
Confidential & Proprietary
2 Stories
1. Focused Learning for the Long-Tail
2. Factorized Deep Retrieval
29
Confidential & Proprietary
YouTube WatchNext
impression
videos
watch video
30
Confidential & Proprietary
Motivation
● Nominate best candidates
from many videos
● Predict good co-watch
patterns for fresh and tail
videos
?
31
Confidential & Proprietary
Deep Retrieval: A bit of history
Deep retrieval: Large-scale machine-learned item retrieval
[2013] Sibyl Deep Retrieval
Sibyl model (linear) + token indexing
[2017] TFX Factorized Deep Retrieval
WALS model (bilinear factorization) + ScaM
32
Confidential & Proprietary
Serving Flow
Huge item corpus
1,000 candidates
Offline
refinement
ranker
deep retrieval
nominator
online
re-ranker
other
candidate
generators
33
Confidential & Proprietary
Serving Flow
1,000 candidates
Offline
refinement
ranker
deep retrieval
nominator
Challenges
● index-friendly ML model
● generalizes well
● scores accurately
● avoids WTFs
online
re-ranker
other
candidate
generators
34
Huge item corpus
Confidential & Proprietary
WALS factorization
P U VT
35
Confidential & Proprietary
WALS factorization
● Loss function:
● : 1. Prior on implicit negatives; 2. Control the degree of generalization
● Scalable training: Linear convergence by AltMin. Distributed TF implementation (1B * 1B)
P U VT
36
Confidential & Proprietary
Collective matrix factorization
Limitations of vanilla factorization:
1. Fixed vocabs
2. Does not make use of features.
watch videos
impression
videos
A
37
Confidential & Proprietary
Collective matrix factorization: learning feature representation
Limitations of vanilla factorization:
1. Fixed vocabs
2. Does not make use of features.
Solution: Co-embed features and items.
● Learns the representation of features
and items simultaneously.
● Key to learning Item and Feature
latent factors is to zero-initialize
submatrix D.
features of
watch videos
watch videos
impression
videos
features of
impression
videos
AB
CT
D
38
Confidential & Proprietary
features of
watch videos
watch videos
topic: pop music keyword: sugar channel: maroon 5
1 1 1
impression
videos
features of
impression
videos
AB
CT
D
39
Collective matrix factorization: learning feature representation
Confidential & Proprietary
Model tuning for missing observations
features of
watch videos
watch videos
impression
videos
features of
impression
videos
AB
CT
D
40
Remove all data points from submatrix A.
Confidential & Proprietary
Model tuning for missing observations
features of
watch videos
watch videos
impression
videos
features of
impression
videos
AB
CT
D
Cosine dist between proj and
original embeddings
Reproject videos using only feature
embeddings to predict their co-watch patterns.
41
Confidential & ProprietaryConfidential & Proprietary
especially on newly
uploaded videos.
Improvement on
overall viewership
42
Confidential & Proprietary
WALS Factorization
● Full TensorFlow implementation
○ Custom-ops/kernels for alternating minimization.
● Single-Machine Version
○ tf.learn.Estimator API
○ Open-sourced in tf.contrib
● Distributed Version
○ (not yet available externally)
○ Specialized Synchronization Control with Exact
Synchronized Row/Column Sweep Switching.
○ Fault tolerant.
○ Scalable. 400M x 400M x 200D trained in 1 ~ 3 days.
○ Moving to tf.Estimator Interface with TFX integration.
43
TF WALS
models
AB
CT
D
Training
Confidential & Proprietary
C++ and TensorFlow Serving backends
● Distributed TensorFlow Serving using Remote-session-run-op
○ Support embedding lookup and multi-sharded nearest-neighbor lookups.
● Serving a 1.2TB model in TensorFlow Serving!
Embedding
lookup graph
(sharded)
Master
graph
ScaM graph
(sharded)
44
User
Request
TF WALS
models
AB
CT
D
Training Input
Serving Training
Confidential & Proprietary
The Lesson
Modeling the long-tail items/users requires
special techniques and infrastructure
45
Confidential & Proprietary
The Lesson
Modeling the long-tail items/users requires
special techniques and infrastructure:
Focused Learning & Factorized Deep Retrieval
46
Thank you! Questions?
47
Learning Item and User Representations with
Sparse Data in Recommender Systems
Contact: edchi@google.com
Joint work with:
● Focused Learning: Alex Beutel, Zhiyuan Cheng, Hubert Pham, John Anderson
● Factorized DR: Xinyang Yi, Yifan Chen, Lichan Hong, Xiang Wu, Sukriti Ramesh,
Noah Fiedel, & from YouTube: Lukasz Heldt, Nandini, Nandini Seshadri
48

More Related Content

What's hot

Deep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps WorkflowsDeep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps WorkflowsBill Liu
 
Weekly #106: Deep Learning on Mobile
Weekly #106: Deep Learning on MobileWeekly #106: Deep Learning on Mobile
Weekly #106: Deep Learning on MobileBill Liu
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLPaco Nathan
 
Model Drift Monitoring using Tensorflow Model Analysis
Model Drift Monitoring using Tensorflow Model AnalysisModel Drift Monitoring using Tensorflow Model Analysis
Model Drift Monitoring using Tensorflow Model AnalysisVivek Raja P S
 
Metaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixMetaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixBill Liu
 
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...SigOpt
 
Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101QuantUniversity
 
Managing and Versioning Machine Learning Models in Python
Managing and Versioning Machine Learning Models in PythonManaging and Versioning Machine Learning Models in Python
Managing and Versioning Machine Learning Models in PythonSimon Frid
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016MLconf
 
GDG PDX - An Intro to Google Cloud AutoML Vision
GDG PDX - An Intro to Google Cloud AutoML VisionGDG PDX - An Intro to Google Cloud AutoML Vision
GDG PDX - An Intro to Google Cloud AutoML Visionjerryhargrove
 
TFX: A tensor flow-based production-scale machine learning platform
TFX: A tensor flow-based production-scale machine learning platformTFX: A tensor flow-based production-scale machine learning platform
TFX: A tensor flow-based production-scale machine learning platformShunya Ueta
 
AISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeAISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeBill Liu
 
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine LearningWeekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine LearningBill Liu
 
Productionizing Deep Reinforcement Learning with Spark and MLflow
Productionizing Deep Reinforcement Learning with Spark and MLflowProductionizing Deep Reinforcement Learning with Spark and MLflow
Productionizing Deep Reinforcement Learning with Spark and MLflowDatabricks
 
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...Natalia Díaz Rodríguez
 
MATLAB Programming Projects Research Help
MATLAB Programming Projects Research HelpMATLAB Programming Projects Research Help
MATLAB Programming Projects Research HelpMatlab Simulation
 
Machine Learning Using Cloud Services
Machine Learning Using Cloud ServicesMachine Learning Using Cloud Services
Machine Learning Using Cloud ServicesSC5.io
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systemsXavier Amatriain
 
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...Shortening the time from analysis to deployment with ml as-a-service — Luiz A...
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...PAPIs.io
 

What's hot (20)

Deep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps WorkflowsDeep AutoViML For Tensorflow Models and MLOps Workflows
Deep AutoViML For Tensorflow Models and MLOps Workflows
 
Weekly #106: Deep Learning on Mobile
Weekly #106: Deep Learning on MobileWeekly #106: Deep Learning on Mobile
Weekly #106: Deep Learning on Mobile
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAML
 
Model Drift Monitoring using Tensorflow Model Analysis
Model Drift Monitoring using Tensorflow Model AnalysisModel Drift Monitoring using Tensorflow Model Analysis
Model Drift Monitoring using Tensorflow Model Analysis
 
Metaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixMetaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at Netflix
 
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...
MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...
 
Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101
 
Managing and Versioning Machine Learning Models in Python
Managing and Versioning Machine Learning Models in PythonManaging and Versioning Machine Learning Models in Python
Managing and Versioning Machine Learning Models in Python
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
 
GDG PDX - An Intro to Google Cloud AutoML Vision
GDG PDX - An Intro to Google Cloud AutoML VisionGDG PDX - An Intro to Google Cloud AutoML Vision
GDG PDX - An Intro to Google Cloud AutoML Vision
 
TFX: A tensor flow-based production-scale machine learning platform
TFX: A tensor flow-based production-scale machine learning platformTFX: A tensor flow-based production-scale machine learning platform
TFX: A tensor flow-based production-scale machine learning platform
 
AISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeAISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the Edge
 
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine LearningWeekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
 
Productionizing Deep Reinforcement Learning with Spark and MLflow
Productionizing Deep Reinforcement Learning with Spark and MLflowProductionizing Deep Reinforcement Learning with Spark and MLflow
Productionizing Deep Reinforcement Learning with Spark and MLflow
 
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...
A Folksonomy of styles, aka: other stylists also said and Subjective Influenc...
 
MATLAB Programming Projects Research Help
MATLAB Programming Projects Research HelpMATLAB Programming Projects Research Help
MATLAB Programming Projects Research Help
 
Oa 4 month exp
Oa 4 month expOa 4 month exp
Oa 4 month exp
 
Machine Learning Using Cloud Services
Machine Learning Using Cloud ServicesMachine Learning Using Cloud Services
Machine Learning Using Cloud Services
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems
 
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...Shortening the time from analysis to deployment with ml as-a-service — Luiz A...
Shortening the time from analysis to deployment with ml as-a-service — Luiz A...
 

Viewers also liked

Parameter Server Approach for Online Learning at Twitter
Parameter Server Approach for Online Learning at TwitterParameter Server Approach for Online Learning at Twitter
Parameter Server Approach for Online Learning at TwitterZhiyong (Joe) Xie
 
Horovod - Distributed TensorFlow Made Easy
Horovod - Distributed TensorFlow Made EasyHorovod - Distributed TensorFlow Made Easy
Horovod - Distributed TensorFlow Made EasyAlexander Sergeev
 
Large-Scale Training with GPUs at Facebook
Large-Scale Training with GPUs at FacebookLarge-Scale Training with GPUs at Facebook
Large-Scale Training with GPUs at FacebookFaisal Siddiqi
 
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...Sébastien Bourguignon
 
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Sujit Pal
 
Understanding Feature Space in Machine Learning
Understanding Feature Space in Machine LearningUnderstanding Feature Space in Machine Learning
Understanding Feature Space in Machine LearningAlice Zheng
 

Viewers also liked (6)

Parameter Server Approach for Online Learning at Twitter
Parameter Server Approach for Online Learning at TwitterParameter Server Approach for Online Learning at Twitter
Parameter Server Approach for Online Learning at Twitter
 
Horovod - Distributed TensorFlow Made Easy
Horovod - Distributed TensorFlow Made EasyHorovod - Distributed TensorFlow Made Easy
Horovod - Distributed TensorFlow Made Easy
 
Large-Scale Training with GPUs at Facebook
Large-Scale Training with GPUs at FacebookLarge-Scale Training with GPUs at Facebook
Large-Scale Training with GPUs at Facebook
 
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...
Olivier Mathiot - Rakuten PriceMinister - Extrait Livre Blanc 100 #PortraitDe...
 
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
 
Understanding Feature Space in Machine Learning
Understanding Feature Space in Machine LearningUnderstanding Feature Space in Machine Learning
Understanding Feature Space in Machine Learning
 

Similar to 2017 10-10 (netflix ml platform meetup) learning item and user representations with sparse data in recommender systems (focused learning, factorized deep retrieval)

Teacher training material
Teacher training materialTeacher training material
Teacher training materialVikram Parmar
 
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Carol Smith
 
Generative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxGenerative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxSri Ambati
 
Udacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsUdacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsAxel de Romblay
 
[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation SystemsAxel de Romblay
 
Maintaining Large Scale Julia Ecosystems
Maintaining Large Scale Julia EcosystemsMaintaining Large Scale Julia Ecosystems
Maintaining Large Scale Julia EcosystemsChris Rackauckas
 
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...ssuser610732
 
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Human-Centered Artificial Intelligence: Reliable, Safe & TrustworthyHuman-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Human-Centered Artificial Intelligence: Reliable, Safe & TrustworthyJalnaAfridi
 
How to Build Winning Products by Microsoft Sr. Product Manager
How to Build Winning Products by Microsoft Sr. Product ManagerHow to Build Winning Products by Microsoft Sr. Product Manager
How to Build Winning Products by Microsoft Sr. Product ManagerProduct School
 
A flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVA flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVIntoTheMinds
 
A Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVA Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVFrancisco Couto
 
User Research Fast & Cheap
User Research Fast & Cheap User Research Fast & Cheap
User Research Fast & Cheap John H Douglass
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Sudeep Das, Ph.D.
 
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinRapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinAviva Rosenstein
 
Intro to Product Management
Intro to Product Management Intro to Product Management
Intro to Product Management Ria Sankar
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Xavier Amatriain
 
Learning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsLearning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsClaudia Hauff
 
ASA conference Feb 2013
ASA conference Feb 2013ASA conference Feb 2013
ASA conference Feb 2013mrkwr
 

Similar to 2017 10-10 (netflix ml platform meetup) learning item and user representations with sparse data in recommender systems (focused learning, factorized deep retrieval) (20)

Teacher training material
Teacher training materialTeacher training material
Teacher training material
 
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
Users are Losers! They’ll Like Whatever we Make! and Other Fallacies.
 
Generative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxGenerative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptx
 
Udacity webinar on Recommendation Systems
Udacity webinar on Recommendation SystemsUdacity webinar on Recommendation Systems
Udacity webinar on Recommendation Systems
 
[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems[UPDATE] Udacity webinar on Recommendation Systems
[UPDATE] Udacity webinar on Recommendation Systems
 
Maintaining Large Scale Julia Ecosystems
Maintaining Large Scale Julia EcosystemsMaintaining Large Scale Julia Ecosystems
Maintaining Large Scale Julia Ecosystems
 
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...
EXTRA: Integrating External Knowledge into Multimodal Hashtag Recommendation ...
 
Practical Usability
Practical UsabilityPractical Usability
Practical Usability
 
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Human-Centered Artificial Intelligence: Reliable, Safe & TrustworthyHuman-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
 
How to Build Winning Products by Microsoft Sr. Product Manager
How to Build Winning Products by Microsoft Sr. Product ManagerHow to Build Winning Products by Microsoft Sr. Product Manager
How to Build Winning Products by Microsoft Sr. Product Manager
 
A flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TVA flexible recommenndation system for Cable TV
A flexible recommenndation system for Cable TV
 
A Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TVA Flexible Recommendation System for Cable TV
A Flexible Recommendation System for Cable TV
 
Josh Aberant - Data-Driven Digital Growth
Josh Aberant - Data-Driven Digital GrowthJosh Aberant - Data-Driven Digital Growth
Josh Aberant - Data-Driven Digital Growth
 
User Research Fast & Cheap
User Research Fast & Cheap User Research Fast & Cheap
User Research Fast & Cheap
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
 
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva RosensteinRapid User Research - a talk from Agile 2013 by Aviva Rosenstein
Rapid User Research - a talk from Agile 2013 by Aviva Rosenstein
 
Intro to Product Management
Intro to Product Management Intro to Product Management
Intro to Product Management
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
 
Learning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsLearning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestions
 
ASA conference Feb 2013
ASA conference Feb 2013ASA conference Feb 2013
ASA conference Feb 2013
 

More from Ed Chi

HCI Korea 2012 Keynote Talk on Model-Driven Research in Social Computing
HCI Korea 2012 Keynote Talk on Model-Driven Research in Social ComputingHCI Korea 2012 Keynote Talk on Model-Driven Research in Social Computing
HCI Korea 2012 Keynote Talk on Model-Driven Research in Social ComputingEd Chi
 
Location and Language in Social Media (Stanford Mobi Social Invited Talk)
Location and Language in Social Media (Stanford Mobi Social Invited Talk)Location and Language in Social Media (Stanford Mobi Social Invited Talk)
Location and Language in Social Media (Stanford Mobi Social Invited Talk)Ed Chi
 
Crowdsourcing using MTurk for HCI research
Crowdsourcing using MTurk for HCI researchCrowdsourcing using MTurk for HCI research
Crowdsourcing using MTurk for HCI researchEd Chi
 
CIKM 2011 Social Computing Industry Invited Talk
CIKM 2011 Social Computing Industry Invited TalkCIKM 2011 Social Computing Industry Invited Talk
CIKM 2011 Social Computing Industry Invited TalkEd Chi
 
WikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteWikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteEd Chi
 
CSCL 2011 Keynote on Social Computing and eLearning
CSCL 2011 Keynote on Social Computing and eLearningCSCL 2011 Keynote on Social Computing and eLearning
CSCL 2011 Keynote on Social Computing and eLearningEd Chi
 
Replication is more than Duplication: Position slides for CHI2011 panel on re...
Replication is more than Duplication: Position slides for CHI2011 panel on re...Replication is more than Duplication: Position slides for CHI2011 panel on re...
Replication is more than Duplication: Position slides for CHI2011 panel on re...Ed Chi
 
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI Research
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI ResearchTutorial on Using Amazon Mechanical Turk (MTurk) for HCI Research
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI ResearchEd Chi
 
Crowdsourcing for HCI Research with Amazon Mechanical Turk
Crowdsourcing for HCI Research with Amazon Mechanical TurkCrowdsourcing for HCI Research with Amazon Mechanical Turk
Crowdsourcing for HCI Research with Amazon Mechanical TurkEd Chi
 
Eddi: Topic Browsing of Twitter Streams
Eddi: Topic Browsing of Twitter StreamsEddi: Topic Browsing of Twitter Streams
Eddi: Topic Browsing of Twitter StreamsEd Chi
 
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...Ed Chi
 
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...Ed Chi
 
Zerozero88 Twitter URL Item Recommender
Zerozero88 Twitter URL Item RecommenderZerozero88 Twitter URL Item Recommender
Zerozero88 Twitter URL Item RecommenderEd Chi
 
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006Ed Chi
 
Model-Driven Research in Social Computing
Model-Driven Research in Social ComputingModel-Driven Research in Social Computing
Model-Driven Research in Social ComputingEd Chi
 
ASC Disaster Response Proposal from Aug 2007
ASC Disaster Response Proposal from Aug 2007ASC Disaster Response Proposal from Aug 2007
ASC Disaster Response Proposal from Aug 2007Ed Chi
 
Using Information Scent to Model Users in Web1.0 and Web2.0
Using Information Scent to Model Users in Web1.0 and Web2.0Using Information Scent to Model Users in Web1.0 and Web2.0
Using Information Scent to Model Users in Web1.0 and Web2.0Ed Chi
 
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...Ed Chi
 
2010-03-10 PARC Augmented Social Cognition Research Overview
2010-03-10 PARC Augmented Social Cognition Research Overview2010-03-10 PARC Augmented Social Cognition Research Overview
2010-03-10 PARC Augmented Social Cognition Research OverviewEd Chi
 
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica SinicaEd Chi
 

More from Ed Chi (20)

HCI Korea 2012 Keynote Talk on Model-Driven Research in Social Computing
HCI Korea 2012 Keynote Talk on Model-Driven Research in Social ComputingHCI Korea 2012 Keynote Talk on Model-Driven Research in Social Computing
HCI Korea 2012 Keynote Talk on Model-Driven Research in Social Computing
 
Location and Language in Social Media (Stanford Mobi Social Invited Talk)
Location and Language in Social Media (Stanford Mobi Social Invited Talk)Location and Language in Social Media (Stanford Mobi Social Invited Talk)
Location and Language in Social Media (Stanford Mobi Social Invited Talk)
 
Crowdsourcing using MTurk for HCI research
Crowdsourcing using MTurk for HCI researchCrowdsourcing using MTurk for HCI research
Crowdsourcing using MTurk for HCI research
 
CIKM 2011 Social Computing Industry Invited Talk
CIKM 2011 Social Computing Industry Invited TalkCIKM 2011 Social Computing Industry Invited Talk
CIKM 2011 Social Computing Industry Invited Talk
 
WikiSym 2011 Closing Keynote
WikiSym 2011 Closing KeynoteWikiSym 2011 Closing Keynote
WikiSym 2011 Closing Keynote
 
CSCL 2011 Keynote on Social Computing and eLearning
CSCL 2011 Keynote on Social Computing and eLearningCSCL 2011 Keynote on Social Computing and eLearning
CSCL 2011 Keynote on Social Computing and eLearning
 
Replication is more than Duplication: Position slides for CHI2011 panel on re...
Replication is more than Duplication: Position slides for CHI2011 panel on re...Replication is more than Duplication: Position slides for CHI2011 panel on re...
Replication is more than Duplication: Position slides for CHI2011 panel on re...
 
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI Research
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI ResearchTutorial on Using Amazon Mechanical Turk (MTurk) for HCI Research
Tutorial on Using Amazon Mechanical Turk (MTurk) for HCI Research
 
Crowdsourcing for HCI Research with Amazon Mechanical Turk
Crowdsourcing for HCI Research with Amazon Mechanical TurkCrowdsourcing for HCI Research with Amazon Mechanical Turk
Crowdsourcing for HCI Research with Amazon Mechanical Turk
 
Eddi: Topic Browsing of Twitter Streams
Eddi: Topic Browsing of Twitter StreamsEddi: Topic Browsing of Twitter Streams
Eddi: Topic Browsing of Twitter Streams
 
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...
Large Scale Social Analytics on Wikipedia, Delicious, and Twitter (presented ...
 
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...
Model-based Research in Human-Computer Interaction (HCI): Keynote at Mensch u...
 
Zerozero88 Twitter URL Item Recommender
Zerozero88 Twitter URL Item RecommenderZerozero88 Twitter URL Item Recommender
Zerozero88 Twitter URL Item Recommender
 
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006
Smart eBooks: ScentIndex and ScentHighlight research published at VAST2006
 
Model-Driven Research in Social Computing
Model-Driven Research in Social ComputingModel-Driven Research in Social Computing
Model-Driven Research in Social Computing
 
ASC Disaster Response Proposal from Aug 2007
ASC Disaster Response Proposal from Aug 2007ASC Disaster Response Proposal from Aug 2007
ASC Disaster Response Proposal from Aug 2007
 
Using Information Scent to Model Users in Web1.0 and Web2.0
Using Information Scent to Model Users in Web1.0 and Web2.0Using Information Scent to Model Users in Web1.0 and Web2.0
Using Information Scent to Model Users in Web1.0 and Web2.0
 
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...
China HCI Symposium 2010 March: Augmented Social Cognition Research from PARC...
 
2010-03-10 PARC Augmented Social Cognition Research Overview
2010-03-10 PARC Augmented Social Cognition Research Overview2010-03-10 PARC Augmented Social Cognition Research Overview
2010-03-10 PARC Augmented Social Cognition Research Overview
 
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica
2010-02-22 Wikipedia MTurk Research talk given in Taiwan's Academica Sinica
 

Recently uploaded

How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 

Recently uploaded (20)

How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 

2017 10-10 (netflix ml platform meetup) learning item and user representations with sparse data in recommender systems (focused learning, factorized deep retrieval)

  • 1. Learning item and user representations with sparse data in recommender systems Ed H. Chi Google Inc. Abstract: Recommenders match users in a particular context with the best personalized items that they will engage with. The problem is that users have shifting item and topic preferences, and give sparse feedback over time (or no-feedback at all). Contexts shift from interaction-to-interaction at various time scales (seconds to minutes to days). Learning about users and items is hard because of noisy and sparse labels, and the user/item set changes rapidly and is large and long-tailed. Given the enormity of the problem, it is a wonder that we learn anything at all about our items and users. In this talk, I will outline some research at Google to tackle the sparsity problem. First, I will summarize some work on focused learning, which suggests that learning about subsets of the data requires tuning the parameters for estimating the missing unobserved entries. Second, we utilize joint feature factorization to impute possible user affinity to freshly-uploaded items, and employ hashing-based techniques to perform extremely fast similarity scoring on a large item catalog, while controlling variance. This approach is currently serving a ~1TB model on production traffic using distributed TensorFlow Serving, demonstrating that our techniques work in practice. I will conclude with some remarks on possible future directions. Bio: Ed is a Research Scientist at Google, leading a team focused on recommendation systems, machine learning, and social interaction research. He has launched significant improvements of recommenders for YouTube, Google Play Store and Google+. With over 35 patents and over 100 research articles, he is known for research on Web and online social systems, and the effects of social signals on user behavior. Prior to Google, he was the Area Manager and Principal Scientist at Palo Alto Research Center‘s Augmented Social Cognition Group, where he led the group in understanding how social systems help groups of people to remember, think and reason. Ed completed his three degrees (B.S., M.S., and Ph.D.) in 6.5 years from University of Minnesota, and has been doing research on software systems since 1993. He has been featured and quoted in the press, including the Economist, Time Magazine, LA Times, and the Associated Press, and has won awards for both teaching and research. In his spare time, Ed is an avid photographer and snowboarder. 1
  • 2. Confidential + Proprietary Ed H. Chi Research Scientist & Manager, MLX/SIR Research team Google Research & Machine Intelligence Learning Item and User Representations with Sparse Data in Recommender Systems
  • 3. Confidential & Proprietary 3 TFXan end-to-end ML platform based on TensorFlow.
  • 4. Confidential & Proprietary John Riedl (1962-2013) (wikipedia) 4
  • 5. Confidential & Proprietary The Recommendation Problem User Context Item 5
  • 6. Confidential & Proprietary f( , ) ≈ The Recommendation Problem User Context Item 6
  • 7. Confidential & Proprietary The Recommendation Problem User Context Item Watch History Source Preferences Demographics Client Last Interaction Leanback or Lean-forward Topic Past user behavior Clickbait / Brand safe? 7
  • 8. Confidential & Proprietary The Recommendation Problem User Context Item Shifting User Preferences; Sparse Feedback 8
  • 9. Confidential & Proprietary The Recommendation Problem User Context Item Shifting User Preferences; Sparse Feedback Dynamic and Changing Contexts 9
  • 10. Confidential & Proprietary The Recommendation Problem User Context Item Noisy & Sparse Labels; Large Changing Item Set Shifting User Preferences; Sparse Feedback Dynamic and Changing Contexts 10
  • 11. Confidential & Proprietary The Recommendation Problem User Context Item Noisy & Sparse Labels; Large Changing Item Set Shifting User Preferences; Sparse Feedback Dynamic and Changing Contexts Oh, and do this with low latency with a huge corpus of users and items! 11
  • 12. Confidential & Proprietary 2 Stories 1. Focused Learning for the Long-Tail 2. Factorized Deep Retrieval 12
  • 13. Confidential & Proprietary The Recommendation Problem 5 3 1 2 1 5 4 3 Users Items 13
  • 14. Confidential & Proprietary The Recommendation Problem Given: Observed (user, item) ratings Find: A model that predicts the missing ratings well5 3 1 2 1 5 4 3 ? ? ? ? ? ? ? ? Users Items 14
  • 15. Confidential & Proprietary Recommender quality inconsistent across movies Error (RMSE) Genre 15
  • 16. Confidential & Proprietary Skewed Data “Globally optimal” = Tyranny of the Majority 16
  • 17. Confidential & Proprietary We don’t represent users/items equally! Per-User Prediction Accuracy Frequency Error (MSE) Per-Movie Prediction Accuracy Frequency Error (MSE) Wanted: A model that predicts well for all users and all items. 17
  • 18. Confidential & Proprietary Focused Learning Problem Definition Given: ● A dataset: R ● Group of items (or users) to focus on: I Find: A model that has high prediction accuracy for RI 18
  • 19. Confidential & Proprietary Approach 1. Focus Selection - Where should the additional models focus? 2. Focused Learning - How can learn a new model to improve prediction on a subset of the data? 19
  • 20. Confidential & Proprietary Approach 1. Focus Selection - Where should the additional models focus? 2. Focused Learning - How can learn a new model to improve prediction on a subset of the data?Subset of columns Movies Users Movies Users Subset of rows “Focus Group” 20
  • 21. Confidential & Proprietary Approach 1. Focus Selection - Where should the additional models focus? 2. Focused Learning - How can learn a new model to improve prediction on a subset of the data? 21
  • 22. Confidential & Proprietary High-Level Approach (1) Learn model (2) Return accuracy on validation set. 22
  • 23. Confidential & Proprietary Focused Hyperparameter Optimization Typical Hyperparameter Optimization (1) Learn model (2) Return accuracy on validation set. 23
  • 24. Confidential & Proprietary Focused Hyperparameter Optimization Typical Hyperparameter Optimization Focused Hyperparameter Optimization (1) Learn matrix factorization model (2) Return accuracy on validation set. Choose model based on focused group! 24
  • 25. Confidential & Proprietary An Example of Focused Learning Allow for different regularization for focus group and “unfocus” group 25
  • 27. Confidential & Proprietary Focus on Cold-Start Movies 27
  • 28. Confidential & Proprietary Summary 1. “Globally optimal” is not best for everybody. Myth of the average user! 2. Learn additional models focused on problematic regions. The long-tail needs different exploration strategies! Per-User Prediction Accuracy Frequency MSE Alex Beutel, Ed H. Chi, Zhiyuan Cheng, Hubert Pham, John Anderson. Beyond Globally Optimal: Focused Learning for Improved Recommendations. In WWW 2017. 28
  • 29. Confidential & Proprietary 2 Stories 1. Focused Learning for the Long-Tail 2. Factorized Deep Retrieval 29
  • 30. Confidential & Proprietary YouTube WatchNext impression videos watch video 30
  • 31. Confidential & Proprietary Motivation ● Nominate best candidates from many videos ● Predict good co-watch patterns for fresh and tail videos ? 31
  • 32. Confidential & Proprietary Deep Retrieval: A bit of history Deep retrieval: Large-scale machine-learned item retrieval [2013] Sibyl Deep Retrieval Sibyl model (linear) + token indexing [2017] TFX Factorized Deep Retrieval WALS model (bilinear factorization) + ScaM 32
  • 33. Confidential & Proprietary Serving Flow Huge item corpus 1,000 candidates Offline refinement ranker deep retrieval nominator online re-ranker other candidate generators 33
  • 34. Confidential & Proprietary Serving Flow 1,000 candidates Offline refinement ranker deep retrieval nominator Challenges ● index-friendly ML model ● generalizes well ● scores accurately ● avoids WTFs online re-ranker other candidate generators 34 Huge item corpus
  • 35. Confidential & Proprietary WALS factorization P U VT 35
  • 36. Confidential & Proprietary WALS factorization ● Loss function: ● : 1. Prior on implicit negatives; 2. Control the degree of generalization ● Scalable training: Linear convergence by AltMin. Distributed TF implementation (1B * 1B) P U VT 36
  • 37. Confidential & Proprietary Collective matrix factorization Limitations of vanilla factorization: 1. Fixed vocabs 2. Does not make use of features. watch videos impression videos A 37
  • 38. Confidential & Proprietary Collective matrix factorization: learning feature representation Limitations of vanilla factorization: 1. Fixed vocabs 2. Does not make use of features. Solution: Co-embed features and items. ● Learns the representation of features and items simultaneously. ● Key to learning Item and Feature latent factors is to zero-initialize submatrix D. features of watch videos watch videos impression videos features of impression videos AB CT D 38
  • 39. Confidential & Proprietary features of watch videos watch videos topic: pop music keyword: sugar channel: maroon 5 1 1 1 impression videos features of impression videos AB CT D 39 Collective matrix factorization: learning feature representation
  • 40. Confidential & Proprietary Model tuning for missing observations features of watch videos watch videos impression videos features of impression videos AB CT D 40 Remove all data points from submatrix A.
  • 41. Confidential & Proprietary Model tuning for missing observations features of watch videos watch videos impression videos features of impression videos AB CT D Cosine dist between proj and original embeddings Reproject videos using only feature embeddings to predict their co-watch patterns. 41
  • 42. Confidential & ProprietaryConfidential & Proprietary especially on newly uploaded videos. Improvement on overall viewership 42
  • 43. Confidential & Proprietary WALS Factorization ● Full TensorFlow implementation ○ Custom-ops/kernels for alternating minimization. ● Single-Machine Version ○ tf.learn.Estimator API ○ Open-sourced in tf.contrib ● Distributed Version ○ (not yet available externally) ○ Specialized Synchronization Control with Exact Synchronized Row/Column Sweep Switching. ○ Fault tolerant. ○ Scalable. 400M x 400M x 200D trained in 1 ~ 3 days. ○ Moving to tf.Estimator Interface with TFX integration. 43 TF WALS models AB CT D Training
  • 44. Confidential & Proprietary C++ and TensorFlow Serving backends ● Distributed TensorFlow Serving using Remote-session-run-op ○ Support embedding lookup and multi-sharded nearest-neighbor lookups. ● Serving a 1.2TB model in TensorFlow Serving! Embedding lookup graph (sharded) Master graph ScaM graph (sharded) 44 User Request TF WALS models AB CT D Training Input Serving Training
  • 45. Confidential & Proprietary The Lesson Modeling the long-tail items/users requires special techniques and infrastructure 45
  • 46. Confidential & Proprietary The Lesson Modeling the long-tail items/users requires special techniques and infrastructure: Focused Learning & Factorized Deep Retrieval 46
  • 47. Thank you! Questions? 47 Learning Item and User Representations with Sparse Data in Recommender Systems Contact: edchi@google.com Joint work with: ● Focused Learning: Alex Beutel, Zhiyuan Cheng, Hubert Pham, John Anderson ● Factorized DR: Xinyang Yi, Yifan Chen, Lichan Hong, Xiang Wu, Sukriti Ramesh, Noah Fiedel, & from YouTube: Lukasz Heldt, Nandini, Nandini Seshadri
  • 48. 48