Recommending What Video to Watch Next: A Multitask Ranking System

被引：208

作者：

Zhao, Zhe ^{[1
]}

Hong, Lichan ^{[1
]}

Wei, Li ^{[1
]}

Chen, Jilin ^{[1
]}

Nath, Aniruddh ^{[1
]}

Andrews, Shawn ^{[1
]}

Kumthekar, Aditee ^{[1
]}

Sathiamoorthy, Maheswaran ^{[1
]}

Yi, Xinyang ^{[1
]}

Chi, Ed ^{[1
]}

机构：

[1] Google Inc, Mountain View, CA 94043 USA

来源：

RECSYS 2019: 13TH ACM CONFERENCE ON RECOMMENDER SYSTEMS | 2019年

关键词：

Recommendation and Ranking; Multitask Learning; Selection Bias;

D O I：

10.1145/3298689.3346997

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we introduce a large scale multi-objective ranking system for recommending what video to watch next on an industrial video sharing platform. The system faces many real-world challenges, including the presence of multiple competing ranking objectives, as well as implicit selection biases in user feedback. To tackle these challenges, we explored a variety of soft-parameter sharing techniques such as Multi-gate Mixture-of-Experts so as to efficiently optimize for multiple ranking objectives. Additionally, we mitigated the selection biases by adopting a Wide & Deep framework. We demonstrated that our proposed techniques can lead to substantial improvements on recommendation quality on one of the world's largest video sharing platforms.

引用

页码：43 / 51

页数：9

共 45 条

[11] Deep Neural Networks for YouTube Recommendations [J].

Covington, Paul ;

Adams, Jay ;

Sargin, Emre .

PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, :191-198

[12]

Davidson J., 2010, Proceedings of the fourth ACM conference on Recommender systems, P293, DOI [DOI 10.1145/1864708.1864770, 10.1145/1864708.1864770]

[13]

Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171

[14]

Ehsan H, 2016, PROC INT CONF DATA, P731, DOI 10.1109/ICDE.2016.7498285

[15]

Eksombatchai C, 2018, WEB CONFERENCE 2018: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW2018), P1775

[16] A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems [J].

Elkahky, Ali ;

Song, Yang ;

He, Xiaodong .

PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW 2015), 2015, :278-288

[17] Practical Lessons from Developing a Large-Scale Recommender System at Zalando [J].

Freno, Antonino .

PROCEEDINGS OF THE ELEVENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'17), 2017, :251-259

[18] Offline and Online Evaluation of News Recommender Systems at swissinfo.ch [J].

Garcin, Florent ;

Faltings, Boi ;

Donatsch, Olivier ;

Alazzawi, Ayar ;

Bruttin, Christophe ;

Huber, Amr .

PROCEEDINGS OF THE 8TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'14), 2014, :169-176

[19] A Neural Labeled Network Embedding Approach to Product Adopter Prediction [J].

Gu, Qi ;

Bai, Ting ;

Zhao, Wayne Xin ;

Wen, Ji-Rong .

INFORMATION RETRIEVAL TECHNOLOGY (AIRS 2018), 2018, 11292 :77-89

[20]

Gupta Pankaj, 2013, P 22 INT C WORLD WID, P505, DOI DOI 10.1145/2488388.2488433

← 1 2 3 4 5 →