Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion

TL;DR

This paper introduces DMAE, a novel auto-encoder model that dynamically fuses multimodal user interest information at the behavioral level, addressing data sparsity and improving recommendation accuracy.

Contribution

It proposes a distribution-guided auto-encoder for cross-fusing multimodal user interests based on behavioral sequences, overcoming limitations of early fusion methods.

Findings

DMAE outperforms existing multimodal recommendation models.

The model effectively captures dynamic user interests.

Extensive experiments validate its superiority.

Abstract

Traditional recommendation methods rely on correlating the embedding vectors of item IDs to capture implicit collaborative filtering signals to model the user's interest in the target item. Consequently, traditional ID-based methods often encounter data sparsity problems stemming from the sparse nature of ID features. To alleviate the problem of item ID sparsity, recommendation models incorporate multimodal item information to enhance recommendation accuracy. However, existing multimodal recommendation methods typically employ early fusion approaches, which focus primarily on combining text and image features, while neglecting the contextual influence of user behavior sequences. This oversight prevents dynamic adaptation of multimodal interest representations based on behavioral patterns, consequently restricting the model's capacity to effectively capture user multimodal interests. Therefore, this paper proposes the Distribution-Guided Multimodal-Interest Auto-Encoder (DMAE), which achieves the cross fusion of user multimodal interest at the behavioral level.Ultimately, extensive experiments demonstrate the superiority of DMAE.