Alphabet - Revision history

Zeno Gantner: /* Papers */

2024-03-13T11:32:59Z

Papers

Zeno Gantner: /* Papers */

2023-10-04T17:01:48Z

Papers

Zeno Gantner: /* Papers */

2023-10-04T17:01:20Z

Papers

Zeno Gantner: /* Blog posts */

2023-08-08T08:54:20Z

Blog posts

Zeno Gantner: /* Papers */

2023-07-20T12:26:14Z

Papers

Zeno Gantner: /* Papers */

2023-07-20T12:24:58Z

Papers

Zeno Gantner: /* Papers */

2023-06-27T11:58:06Z

Papers

Zeno Gantner: /* Papers */

2023-06-21T13:40:32Z

Papers

Zeno Gantner at 19:20, 3 December 2022

2022-12-03T19:20:14Z

Zeno Gantner: Created page with "'''Alphabet''' is the parent company of '''Google''' and many of its (former) subsidiaries, for example '''YouTube''' and '''DeepMind''' == Tutorials == # [https://develope..."

2022-12-03T19:16:58Z

Created page with "'''Alphabet''' is the parent company of '''Google''' and many of its (former) subsidiaries, for example '''YouTube''' and '''DeepMind''' == Tutorials == # [https://develope..."

New page

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

== Tutorials ==

# [https://developers.google.com/machine-learning/guides/rules-of-ml Rules of Machine Learning]

== Papers ==

# {{ops}} [https://research.google/pubs/pub51712/ Data Management Principles], book chapter in ''Reliable Machine Learning: Applying SRE Principles to ML in Production'', 2022
# {{neural}} [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/827afbd792b84f20bf1b439d1d678e121c9cfa46.pdf Scale Calibration of Deep Ranking Models], [[KDD 2022]]
# [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/bfbc205383e9fc0aa132011c587d5f826ba90274.pdf Bootstrapping Recommendations at Chrome Web Store], [[KDD 2021]]
# {{ops}} [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/0d556e45afc54afeb2eb6b51a9bc1827b9961ff4.pdf “Everyone wants to do the model work, not the data work”: Data Cascades in High-Stakes AI], [[CHI 2021]]
# {{ltor}}{{neural}} [https://openreview.net/pdf/033e77d13245fbc5492689e8b06afbfd433384d8.pdf Are Neural Rankers Still Outperformed By Gradient Boosted Decision Trees?], [[ICLR 2021]]
# {{explanations}} [https://dl.acm.org/doi/pdf/10.1145/3397271.3401032 Measuring Recommendation Explanation Quality: The Conflicting Goals of Explanations], [[RecSys 2021]]
# [https://arxiv.org/pdf/2101.08769.pdf 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
# [https://research.google/pubs/pub49284/ Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems]
# {{bandits}} [[https://proceedings.neurips.cc/paper/2020/hash/9b7c8d13e4b2f08895fb7bcead930b46-Abstract.html|Latent Bandits Revisited]], [[NeurIPS 2020]]
# [https://papers.nips.cc/paper/2020/file/070dbb6024b5ef93784428afc71f2146-Paper.pdf Rankmax: An Adaptive Projection Alternative to the Softmax Function], [[NeurIPS 2020]]
# {{performance}} [http://proceedings.mlr.press/v108/han20b.html MAP Inference for Customized Determinantal Point Processes via Maximum Inner Product Search], [[AISTATS 2020]]
# {{ltor}} [https://arxiv.org/abs/2005.02553 Interpretable Learning-to-Rank with Generalized Additive Models], 2020
# [https://dl.acm.org/doi/abs/10.1145/3366423.3380130 Off-policy Learning in Two-stage Recommender Systems], [[WWW 2020]]
# {{neural}} [https://dl.acm.org/doi/pdf/10.1145/3366424.3386195 Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations], [[WWW 2020]]; Google Play
# {{bias}} [https://research.google/pubs/pub49273/ Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies], [[KDD 2020]]
# {{neural}} [https://dl.acm.org/doi/10.1145/3383313.3412488 Neural Collaborative Filtering vs. Matrix Factorization Revisited], [[RecSys 2020]]
# [https://arxiv.org/abs/2008.02930 Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval], [[CIKM 2020]]
# {{ltor}} [https://arxiv.org/abs/2008.13535 DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems], 2020
# {{runtime}} [https://arxiv.org/abs/1908.10396 Accelerating Large-Scale Inference with Anisotropic Vector Quantization], 2019
# [https://arxiv.org/pdf/1905.12767.pdf Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology], 2019
# [https://arxiv.org/pdf/1810.02019.pdf Seq2Slate: Re-ranking and Slate Optimization with RNNs], 2019
# {{neural}} [https://dl.acm.org/doi/pdf/10.1145/3331184.3331347 Revisiting Approximate Metric Optimization in the Age of Deep Neural Networks], [[SIGIR 2019]] (short paper)
# {{neural}}[https://research.google/pubs/pub47954/ Towards Neural Mixture Recommender for Long Range Dependent User Sequences], [[WWW 2019]]
# [https://arxiv.org/abs/1812.02353 Top-K Off-Policy Correction for a REINFORCE Recommender System], [[WSDM 2019]]
# {{neural}} [https://arxiv.org/pdf/1902.08588 Towards neural mixture recommender for long range dependent user sequences], [[WWW 2019]]
# {{ltor}} [https://daiwk.github.io/assets/youtube-multitask.pdf Recommending what video to watch next: A multitask ranking system], [[RecSys 2019]]
# {{bias}} [https://research.google/pubs/pub48840/ Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations], [[RecSys 2019]]
# [https://research.google/pubs/pub47705/ Efficient Training on Very Large Corpora via Gramian Estimation], [[ICLR 2019]]
# {{neural}} [https://dl.acm.org/doi/10.1145/3159652.3159727 Latent Cross: Making Use of Context in Recurrent Recommender Systems], [[WSDM 2018]]
# [http://www.alexbeutel.com/papers/q-and-r-kdd2018.pdf Q&R: A two-stage approach toward interactive recommendation], [[KDD 2018]]
# [https://research.google/pubs/pub47630/ Categorical-Attributes-Based Multi-Level Classification for Recommender Systems], [[RecSys 2018]]
# {{neural}}{{bandits}} [https://openreview.net/pdf?id=SyYe6k-CW Deep Bayesian Bandits Showdown: an Empirical Comparison of Bayesian Deep Networks for Thompson Sampling], [[ICLR 2018]]
# {{ltor}} [https://dl.acm.org/doi/pdf/10.1145/3269206.3271784 The LambdaLoss Framework for Ranking Metric Optimization], [[CIKM 2018]]
# {{production}}{{experimentation}} ''[https://dl.acm.org/ft_gateway.cfm?id=3272018&type=pdf Practical Diversified Recommendations on YouTube with Determinantal Point Processes]'', [[CIKM 2018]]
# [https://datalab.csd.auth.gr/~gounaris/icde2018-google-recommendations.pdf Recommendations for All: Solving Thousands of Recommendation Problems Daily], ICDE 2018 (also describe user context representation by the actions taken)
# [https://research.google/pubs/pub46300/ A Generic Coordinate Descent Framework for Learning from Implicit Feedback], [[WWW 2017]]
# {{neural}} [https://arxiv.org/pdf/1708.05123.pdf Deep & Cross Network for Ad Click Predictions], 2017
# {{production}} [https://dl.acm.org/ft_gateway.cfm?id=2959190&type=pdf Deep neural networks for YouTube recommendations], [[RecSys 2016]]; [https://dl.acm.org/doi/abs/10.1145/2959100.2959190 video]
# {{production}}{{neural}} [https://arxiv.org/abs/1606.07792 Wide & Deep Learning for Recommender Systems], DLRS 2016 (workshop on deep learning for recommender systems) – used for Google Play
# [http://www.alexbeutel.com/papers/q-and-r-kdd2018.pdf Q&R: A two-stage approach toward interactive recommendation], KDD 2018 (Google)
# [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/rfp0063-christakopoulou.pdf Towards Conversational Recommender Systems], [[KDD 2016]]
# {{ads}} [https://dl.acm.org/ft_gateway.cfm?id=2788583&type=pdf Focusing on the Long-term: It’s Good for Users and Business], [[KDD 2015]]
# {{ads}} [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/41159.pdf Ad Click Prediction: a View from the Trenches], [[KDD 2013]]
# {{production}} [https://tsinghua-nslab.github.io/seminar/2012Spring/11_3/YouTube_RecSys10.pdf The YouTube video recommendation system], [[RecSys 2010]]
# [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.80.4329&rep=rep1&type=pdf Google news personalization: scalable online collaborative filtering], [[WWW 2007]]

== Talks ==

# [https://slideslive.com/38917655/reinforcement-learning-in-recommender-systems-some-challenges Reinforcement Learning for Recommender Systems: Some Challenges], ICML 2019

== Blog posts ==

# [https://cloud.google.com/blog/topics/developers-practitioners/building-large-scale-recommenders-using-cloud-tpus Building Large Scale Recommenders using Cloud TPUs], 2022-10-07
# [https://ai.googleblog.com/2021/07/advances-in-tf-ranking.html Advances in TF-Ranking], 2021-07-21
# [https://scholar.googleblog.com/2021/02/scholar-recommendations-reloaded.html Scholar Recommendations Reloaded! Fresher, More Relevant, Easier], 2021-02-12
# [https://ai.googleblog.com/2020/07/announcing-scann-efficient-vector.html Announcing ScaNN: Efficient Vector Similarity Search], 2020-07-28
# [https://deepmind.com/blog/article/Advanced-machine-learning-helps-Play-Store-users-discover-personalised-apps Advanced machine learning helps Play Store users discover personalised apps], 2019-11-18

== Software ==

# [https://github.com/google/trax Trax]: end-to-end DL library with focus on clear code and speed; used for transformer models, successor to [https://github.com/tensorflow/tensor2tensor tensor2tensor].
# [https://github.com/google/rax rax], learning-to-rank framework for JAX, [https://research.google/pubs/pub51453/ paper]
# [https://github.com/google-research/recsim RecSim] [https://ai.googleblog.com/2019/11/recsim-configurable-simulation-platform.html blog post]
# [https://github.com/google-research/google-research/tree/master/scann ScaNN (Scalable Nearest Neighbors)]
# [https://www.tensorflow.org/recommenders TensorFlow Recommenders] see also [https://github.com/tensorflow/community/blob/master/sigs/recommenders/CHARTER.md TF Recommenders SIG] and [https://github.com/tensorflow/recommenders-addons TF recommender add-ons]
# [https://github.com/tensorflow/ranking TensorFlow Ranking]

== External link ==

* https://abc.xyz/
* [https://en.wikipedia.org/wiki/Alphabet_Inc. Wikipedia article about Alphabet]
* GitHub repositories:
** [https://github.com/google/ Google]
** [https://github.com/google-research/ Google Research] -- Google Research has a [https://github.com/google-research/google-research mono-repo] with most of their projects.
** [https://github.com/deepmind DeepMind]
** [https://github.com/youtube YouTube]

[[Category:Company]]

@@ Line 9: / Line 9: @@
 == Papers ==
 # [https://dl.acm.org/doi/pdf/10.1145/3604915.3608882 Efficient Data Representation Learning in Google-scale Systems], [[RecSys 2023]]
 # [https://dl.acm.org/doi/pdf/10.1145/3604915.3608792 Online Matching: A Real-time Bandit System for Large-scale Recommendations], RecSys 2023

@@ Line 9: / Line 9: @@
 == Papers ==
 # [https://dl.acm.org/doi/pdf/10.1145/3600097 On Reducing User Interaction Data for Personalization], [[ACM TORS]], 2023
 # [https://arxiv.org/pdf/2306.01720.pdf Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation], [[KDD 2023]]

@@ Line 16: / Line 16: @@
 # [https://research.google/pubs/pub51652/ Surrogate for Long-Term User Experience in Recommender Systems], [[KDD 2022]]
 # {{neural}} [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/827afbd792b84f20bf1b439d1d678e121c9cfa46.pdf Scale Calibration of Deep Ranking Models], KDD 2022
 # [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/bfbc205383e9fc0aa132011c587d5f826ba90274.pdf Bootstrapping Recommendations at Chrome Web Store], [[KDD 2021]]
 # {{ops}} [https://storage.googleapis.com/pub-tools-public-publication-data/pdf/0d556e45afc54afeb2eb6b51a9bc1827b9961ff4.pdf “Everyone wants to do the model work, not the data work”: Data Cascades in High-Stakes AI], [[CHI 2021]]

@@ Line 24: / Line 24: @@
 # {{explanations}} [https://dl.acm.org/doi/pdf/10.1145/3397271.3401032 Measuring Recommendation Explanation Quality: The Conflicting Goals of Explanations], [[RecSys 2021]]
 # [https://arxiv.org/pdf/2101.08769.pdf 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
-# [https://research.google/pubs/pub49284/ Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems]
+# [https://research.google/pubs/pub49284/ Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems], [[WSDM 2021]]
 # {{bandits}} [https://proceedings.neurips.cc/paper/2020/hash/9b7c8d13e4b2f08895fb7bcead930b46-Abstract.html Latent Bandits Revisited], [[NeurIPS 2020]]
 # [https://papers.nips.cc/paper/2020/file/070dbb6024b5ef93784428afc71f2146-Paper.pdf Rankmax: An Adaptive Projection Alternative to the Softmax Function], [[NeurIPS 2020]]

@@ Line 68: / Line 68: @@
 # [https://cloud.google.com/blog/topics/developers-practitioners/building-large-scale-recommenders-using-cloud-tpus Building Large Scale Recommenders using Cloud TPUs], 2022-10-07
 # [https://ai.googleblog.com/2021/07/advances-in-tf-ranking.html Advances in TF-Ranking], 2021-07-21
 # [https://scholar.googleblog.com/2021/02/scholar-recommendations-reloaded.html Scholar Recommendations Reloaded! Fresher, More Relevant, Easier], 2021-02-12

@@ Line 1: / Line 1: @@
-'''Alphabet''' is the parent company of '''Google''' and many of its (former) subsidiaries, for example '''YouTube''' and '''DeepMind'''
+'''Alphabet''' is the parent company of '''Google''' and many of its (former) subsidiaries, for example '''YouTube''' and '''DeepMind'''.
@@ Line 5: / Line 5: @@
 # [https://developers.google.com/machine-learning/guides/rules-of-ml Rules of Machine Learning]
 == Papers ==