Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation

TL;DR

This paper introduces Adap-$\tau$, an adaptive method for modulating embedding magnitudes in recommender systems, improving performance by dynamically adjusting normalization temperature to address sensitivity issues.

Contribution

It proposes a novel adaptive strategy for setting the normalization temperature $\tau$, enhancing recommendation accuracy and stability across different datasets.

Findings

Achieves an average of 9% performance gain on four datasets

Demonstrates robustness and personalization in embedding normalization

Validates effectiveness through extensive experiments

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 $\tau$ which controls the scale of the normalized embeddings. To fully foster the merits of the normalization while circumvent its limitation, this work studied on how to adaptively set the proper $\tau$. Towards this end, we first make a comprehensive analyses of $\tau$ to fully understand its role on recommendation. We then accordingly develop an adaptive fine-grained strategy Adap-$\tau$ for the temperature with satisfying four desirable properties including adaptivity, personalized, efficiency and model-agnostic. Extensive experiments have been conducted to validate the effectiveness of the proposal. The code is available at \url{https://github.com/junkangwu/Adap_tau}.