Litcius/Paper detail

Adap-τ : Adaptively Modulating Embedding Magnitude for Recommendation

Jiawei Chen, Junkang Wu, Jiancan Wu, Xuezhi Cao, Sheng Zhou, Xiangnan He

202328 citationsDOIOpen Access PDF

Abstract

Recent years have witnessed the great successes of embedding-based methods in recommender systems. Despite their decent performance, we argue one potential limitation of these methods — the embedding magnitude has not been explicitly modulated, which may aggravate popularity bias and training instability, hindering the model from making a good recommendation. It motivates us to leverage the embedding normalization in recommendation. By normalizing user/item embeddings to a specific value, we empirically observe impressive performance gains (9% on average) on four real-world datasets. Although encouraging, we also reveal a serious limitation when applying normalization in recommendation — the performance is highly sensitive to the choice of the temperature τ which controls the scale of the normalized embeddings.

Topics & Concepts

EmbeddingLeverage (statistics)Normalization (sociology)Computer sciencePopularityRecommender systemMachine learningArtificial intelligenceTheoretical computer scienceSocial psychologyPsychologyAnthropologySociologyRecommender Systems and TechniquesAdvanced Bandit Algorithms ResearchTopic Modeling