BeFA: A General Behavior-driven Feature Adapter for Multimedia Recommendation

TL;DR

This paper introduces BeFA, a behavior-driven feature adapter that reconstructs content features in multimedia recommender systems to better reflect user preferences, addressing issues of information drift and omission.

Contribution

It proposes a novel, general adapter that reconstructs content features guided by behavioral data, improving recommendation accuracy across various methods.

Findings

BeFA improves recommendation performance across multiple models.

The attribution analysis reveals issues of information drift and omission.

Extensive experiments validate the effectiveness of BeFA.

Abstract

Multimedia recommender systems focus on utilizing behavioral information and content information to model user preferences. Typically, it employs pre-trained feature encoders to extract content features, then fuses them with behavioral features. However, pre-trained feature encoders often extract features from the entire content simultaneously, including excessive preference-irrelevant details. We speculate that it may result in the extracted features not containing sufficient features to accurately reflect user preferences. To verify our hypothesis, we introduce an attribution analysis method for visually and intuitively analyzing the content features. The results indicate that certain products' content features exhibit the issues of information drift}and information omission,reducing the expressive ability of features. Building upon this finding, we propose an effective and efficient general Behavior-driven Feature Adapter (BeFA) to tackle these issues. This adapter reconstructs the content feature with the guidance of behavioral information, enabling content features accurately reflecting user preferences. Extensive experiments demonstrate the effectiveness of the adapter across all multimedia recommendation methods. Our code is made publicly available on https://github.com/fqldom/BeFA.