2020

Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations

Gao, Weihao, Fan, Xiangjun, Wang, Chong et al.

Understand

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time.

Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates.
In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g.
clicks) without resorting to the Euclidean space assumption in ANN algorithms.

Built on

Maximum likelihood from incomplete data via the EM algorithm
Arthur P Dempster, Nan M Laird, and Donald B Rubin. 1977 · 1977
Earlier work this paper cites.
Speech understanding systems: A summary of results of the five-year research effort
D Raj Reddy et al · 1977
Earlier work this paper cites.
Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web . 285–295
Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001 · 2001
Earlier work this paper cites.
Amazon. com recommendations: Item-to-item collaborative filtering
Greg Linden, Brent Smith, and Jeremy York. 2003 · 2003
Earlier work this paper cites.
Efficient computation of frequent and top-k elements in data streams. In International conference on database theory . Springer, 398–412
Ahmed Metwally, Divyakant Agrawal, and Amr El Abbadi. 2005 · 2005
Earlier work this paper cites.
Learning optimal tree models under beam search
Original
Jingwei Zhuo, Ziru Xu, Wei Dai, Han Zhu, Han Li, Jian Xu, and Kun Gai. 2020 · 2006
Earlier work this paper cites.
Probabilistic matrix factorization. In Advances in Neural Information Processing Systems . 1257–1264
Andriy Mnih and Russ R Salakhutdinov. 2008 · 2008
Earlier work this paper cites.
Matrix factorization techniques for recommender systems
Yehuda Koren, Robert Bell, and Chris Volinsky. 2009 · 2009
Earlier work this paper cites.
Bayes optimal multilabel classification via probabilistic classifier chains. In International Conference on Machine Learning (ICML)
Krzysztof Dembczynski, Weiwei Cheng, and Eyke Hüllermeier. 2010 · 2010
Earlier work this paper cites.
Product quantization for nearest neighbor search
Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010 · 2010
Earlier work this paper cites.
Factorization machines. In 2010 IEEE International Conference on Data Mining . IEEE, 995–1000
Steffen Rendle. 2010 · 2010
Earlier work this paper cites.

Similar

Optimized product quantization
Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013 · 2013
Cited alongside, same era.
Rank-based similarity search: Reducing the dimensional dependence
Michael E Houle and Michael Nett. 2014 · 2014
Cited alongside, same era.
Scalable nearest neighbor algorithms for high dimensional data
Marius Muja and David G Lowe. 2014 · 2014
Cited alongside, same era.
Asymmetric LSH (ALSH) for sublinear time maximum inner product search (MIPS). In Advances in Neural Information Processing Systems . 2321–2329
Anshumali Shrivastava and Ping Li. 2014 · 2014
Cited alongside, same era.
The movielens datasets: History and context
F Maxwell Harper and Joseph A Konstan. 2015 · 2015
Cited alongside, same era.
Image-based recommendations on styles and substitutes. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval . 43–52
Julian McAuley, Christopher Targett, Qinfeng Shi, and Anton Van Den Hengel. 2015 · 2015
Cited alongside, same era.
Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM conference on recommender systems . 191–198
Paul Covington, Jay Adams, and Emre Sargin. 2016 · 2016
Cited alongside, same era.
Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web . 507–517
Ruining He and Julian McAuley. 2016 · 2016
Cited alongside, same era.
Log-time and log-space extreme classification
Original
Kalina Jasinska and Nikos Karampatziakis. 2016 · 2016
Cited alongside, same era.
Field-aware factorization machines for CTR prediction. In Proceedings of the 10th ACM Conference on Recommender Systems . 43–50
Yuchin Juan, Yong Zhuang, Wei-Sheng Chin, and Chih-Jen Lin. 2016 · 2016
Cited alongside, same era.
DeepFM: a factorization-machine based neural network for CTR prediction
Original
Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017 · 2017
Cited alongside, same era.

Then

Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web . 173–182
Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017 · 2017
Later among the works it cites.
A New Unbiased and Efficient Class of LSH-Based Samplers and Estimators for Partition Function Computation in Log-Linear Models
Original
Ryan Spring and Anshumali Shrivastava. 2017 · 2017
Later among the works it cites.
Neural discrete representation learning
Aaron Van Den Oord, Oriol Vinyals, et al · 2017
Later among the works it cites.
Learning K-way D-dimensional discrete codes for compact embedding representations
Original
Ting Chen, Martin Renqiang Min, and Yizhou Sun. 2018 · 2018
Later among the works it cites.
Efficient loss-based decoding on graphs for extreme classification
Itay Evron, Edward Moroshko, and Koby Crammer. 2018 · 2018
Later among the works it cites.
Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs
Yury A Malkov and Dmitry A Yashunin. 2018 · 2018
Later among the works it cites.
Learning tree-based deep model for recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . 1079–1088
Han Zhu, Xiang Li, Pengye Zhang, Guozheng Li, Jie He, Han Li, and Kun Gai. 2018 · 2018
Later among the works it cites.
Candidate generation with binary codes for large-scale top-n recommendation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management . 1523–1532
Wang-Cheng Kang and Julian McAuley. 2019 · 2019
Later among the works it cites.
Extreme classification in log memory using count-min sketch: A case study of amazon search with 50m products. In Advances in Neural Information Processing Systems . 13265–13275
Tharun Kumar Reddy Medini, Qixuan Huang, Yiqiu Wang, Vijai Mohan, and Anshumali Shrivastava. 2019 · 2019
Later among the works it cites.
Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. In Advances in Neural Information Processing Systems . 5820–5830
Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, and Shanfeng Zhu. 2019 · 2019
Later among the works it cites.
Joint optimization of tree-based index and deep model for recommender systems. In Advances in Neural Information Processing Systems . 3973–3982
Han Zhu, Daqing Chang, Ziru Xu, Pengye Zhang, Xiang Li, Jie He, Han Li, Jian Xu, and Kun Gai. 2019 · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…