Alphabet

Alphabet is the parent company of Google and many of its (former) subsidiaries, for example YouTube and DeepMind.

Tutorials

1. Rules of Machine Learning
2. 4-hour tutorial on Recommendation Systems

Papers

1. Efficient Data Representation Learning in Google-scale Systems, RecSys 2023
2. Online Matching: A Real-time Bandit System for Large-scale Recommendations, RecSys 2023
3. On Reducing User Interaction Data for Personalization, ACM TORS, 2023
4. Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation, KDD 2023
5. Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction, ??? 2023
6. Recommender Systems with Generative Retrieval, ??? 2023
7. 🔩 Data Management Principles, book chapter in Reliable Machine Learning: Applying SRE Principles to ML in Production, 2022
8. Surrogate for Long-Term User Experience in Recommender Systems, KDD 2022
9. 🧠 Scale Calibration of Deep Ranking Models, KDD 2022
10. 📑🧠🔩 On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models, RecSys 2022
11. Bootstrapping Recommendations at Chrome Web Store, KDD 2021
12. 🔩 “Everyone wants to do the model work, not the data work”: Data Cascades in High-Stakes AI, CHI 2021
13. 📑🧠 Are Neural Rankers Still Outperformed By Gradient Boosted Decision Trees?, ICLR 2021
14. 🔑 Measuring Recommendation Explanation Quality: The Conflicting Goals of Explanations, RecSys 2021
15. Item Recommendation from Implicit Feedback, 2021-01-21 – write-up on item recommendation from positive-only feedback with a focus on algorithms; no experiments, no dealing with bias
16. Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems, WSDM 2021
17. 🎰 Latent Bandits Revisited, NeurIPS 2020
18. Rankmax: An Adaptive Projection Alternative to the Softmax Function, NeurIPS 2020
19. 🏃 MAP Inference for Customized Determinantal Point Processes via Maximum Inner Product Search, AISTATS 2020
20. 📑 Interpretable Learning-to-Rank with Generalized Additive Models, 2020
21. Off-policy Learning in Two-stage Recommender Systems, WWW 2020
22. 🧠 Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations, WWW 2020; Google Play
23. 🤔 Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies, KDD 2020
24. 🧠 Neural Collaborative Filtering vs. Matrix Factorization Revisited, RecSys 2020
25. Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval, CIKM 2020
26. 📑 DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems, 2020
27. Template:Runtime Accelerating Large-Scale Inference with Anisotropic Vector Quantization, 2019
28. Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology, 2019
29. Seq2Slate: Re-ranking and Slate Optimization with RNNs, 2019
30. 🧠 Revisiting Approximate Metric Optimization in the Age of Deep Neural Networks, SIGIR 2019 (short paper)
31. 🧠Towards Neural Mixture Recommender for Long Range Dependent User Sequences, WWW 2019
32. Top-K Off-Policy Correction for a REINFORCE Recommender System, WSDM 2019
33. 🧠 Towards neural mixture recommender for long range dependent user sequences, WWW 2019
34. 📑 Recommending what video to watch next: A multitask ranking system, RecSys 2019
35. 🤔 Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations, RecSys 2019
36. Efficient Training on Very Large Corpora via Gramian Estimation, ICLR 2019
37. 🧠 Latent Cross: Making Use of Context in Recurrent Recommender Systems, WSDM 2018
38. Q&R: A two-stage approach toward interactive recommendation, KDD 2018
39. Categorical-Attributes-Based Multi-Level Classification for Recommender Systems, RecSys 2018
40. 🧠🎰 Deep Bayesian Bandits Showdown: an Empirical Comparison of Bayesian Deep Networks for Thompson Sampling, ICLR 2018
41. 📑 The LambdaLoss Framework for Ranking Metric Optimization, CIKM 2018
42. 🕴🔬 Practical Diversified Recommendations on YouTube with Determinantal Point Processes, CIKM 2018
43. Recommendations for All: Solving Thousands of Recommendation Problems Daily, ICDE 2018 (also describe user context representation by the actions taken)
44. A Generic Coordinate Descent Framework for Learning from Implicit Feedback, WWW 2017
45. 🧠 Deep & Cross Network for Ad Click Predictions, 2017
46. 🕴 Deep neural networks for YouTube recommendations, RecSys 2016; video
47. 🕴🧠 Wide & Deep Learning for Recommender Systems, DLRS 2016 (workshop on deep learning for recommender systems) – used for Google Play
48. Q&R: A two-stage approach toward interactive recommendation, KDD 2018 (Google)
49. Towards Conversational Recommender Systems, KDD 2016
50. 💵 Focusing on the Long-term: It’s Good for Users and Business, KDD 2015
51. 💵 Ad Click Prediction: a View from the Trenches, KDD 2013
52. 🕴 The YouTube video recommendation system, RecSys 2010
53. Google news personalization: scalable online collaborative filtering, WWW 2007

Talks

1. Reinforcement Learning for Recommender Systems: Some Challenges, ICML 2019

Blog posts

1. Building Large Scale Recommenders using Cloud TPUs, 2022-10-07
2. On YouTube's recommendation system, 2021-09-15
3. Advances in TF-Ranking, 2021-07-21
4. Scholar Recommendations Reloaded! Fresher, More Relevant, Easier, 2021-02-12
5. Announcing ScaNN: Efficient Vector Similarity Search, 2020-07-28
6. Advanced machine learning helps Play Store users discover personalised apps, 2019-11-18

Software

1. Trax: end-to-end DL library with focus on clear code and speed; used for transformer models, successor to tensor2tensor.
2. rax, learning-to-rank framework for JAX, paper
3. RecSim blog post
4. ScaNN (Scalable Nearest Neighbors)
5. TensorFlow Recommenders see also TF Recommenders SIG and TF recommender add-ons
6. TensorFlow Ranking

External link

• https://abc.xyz/
• Wikipedia article about Alphabet
• GitHub repositories:
  • Google
  • Google Research -- Google Research has a mono-repo with most of their projects.
  • DeepMind
  • YouTube