Meta-Prod2Vec-Product Embeddings Using Side-Information for Recommendation

被引：147

作者：

Vasile, Flavian ^{[1
]}

Smirnova, Elena ^{[1
]}

Conneau, Alexis ^{[1
,2
]}

机构：

[1] Criteo, Paris, France

[2] Facebook AI Res, Paris, France

来源：

PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16) | 2016年

关键词：

Recommender systems; Embeddings; Neural Networks;

D O I：

10.1145/2959100.2959160

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata. Such scenarios are frequently encountered in applications such as content recommendation, ad targeting and web search. Our method leverages past user interactions with items and their attributes to compute low-dimensional embeddings of items. Specifically, the item metadata is injected into the model as side information to regularize the item embeddings. We show that the new item representations lead to better performance on recommendation tasks on an open music dataset.

引用

页码：225 / 232

页数：8

共 31 条

[1]

Agarwal D, 2009, KDD-09: 15TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, P19

[2]

Ali M, 2011, PROC INT CONF DATA, P1242, DOI 10.1109/ICDE.2011.5767878

[3]

[Anonymous], 2011, Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems, DOI DOI 10.1145/2039320.2039330

[4]

[Anonymous], 2010, P 4 ACM C RECOMMEND

[5]

[Anonymous], 2009, Proceedings of the Third ACM Conference on Recommender Systems

[6]

Bengio Y, 2006, STUD FUZZ SOFT COMP, V194, P137

[7]

Cheng H-T, 2016, P 1 WORKSH DEEP LEAR, P7, DOI DOI 10.1145/2988450.2988454

[8] Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content [J].

Djuric, Nemanja ;

Wu, Hao ;

Radosavljevic, Vladan ;

Grbovic, Mihajlo ;

Bhamidipati, Narayan .

PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW 2015), 2015, :248-255

[9] E-commerce in Your Inbox: Product Recommendations at Scale [J].

Grbovic, Mihajlo ;

Radosavljevic, Vladan ;

Djuric, Nemanja ;

Bhamidipati, Narayan ;

Savla, Jaikit ;

Bhagwan, Varun ;

Sharp, Doug .

KDD'15: PROCEEDINGS OF THE 21ST ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2015, :1809-1818

[10]

Johnson C. C., 2014, DISTRIBUTED MACHINE

← 1 2 3 4 →