Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2020

Abstract

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples — both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy Network (KGPolicy), which works as a reinforcement learning agent to explore high-quality negatives. Specifically, by conducting our designed exploration operations, it navigates from the target positive interaction, adaptively receives knowledgeaware negative signals, and ultimately yields a potential negative item to train the recommender. We tested on a matrix factorization (MF) model equipped with KGPolicy, and it achieves significant improvements over both state-of-the-art sampling methods like DNS [39] and IRGAN [30], and KG-enhanced recommender models like KGAT [32]. Further analyses from different angles provide insights of knowledge-aware sampling. We release the code

Keywords

Recommendation, Knowledge Graph, Negative Sampling

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of The World Wide Web Conference 2020, Taipei, Taiwan, April 20-24

First Page

99

Last Page

109

ISBN

9781450370233

Identifier

10.1145/3366423.3380098

Publisher

ACM

City or Country

Taipei, Taiwan

Additional URL

http://doi.org/10.1145/3366423.3380098

Share

COinS