ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation

TL;DR

This paper investigates the semantic role of ID embeddings in multimodal recommendation, proposing a hierarchical attention and graph convolution approach to enhance content and structural representations, leading to improved recommendation performance.

Contribution

It provides a thorough analysis of ID embeddings' semantics and introduces a novel model integrating ID embeddings with multimodal features using hierarchical attention and graph convolution.

Findings

Outperforms state-of-the-art methods on three datasets

Highlights the importance of fine-grained ID embeddings

Demonstrates effectiveness of combining content and structural features

Abstract

Multimodal recommendation aims to model user and item representations comprehensively with the involvement of multimedia content for effective recommendations. Existing research has shown that it is beneficial for recommendation performance to combine (user- and item-) ID embeddings with multimodal salient features, indicating the value of IDs. However, there is a lack of a thorough analysis of the ID embeddings in terms of feature semantics in the literature. In this paper, we revisit the value of ID embeddings for multimodal recommendation and conduct a thorough study regarding its semantics, which we recognize as subtle features of \emph{content} and \emph{structure}. Based on our findings, we propose a novel recommendation model by incorporating ID embeddings to enhance the salient features of both content and structure. Specifically, we put forward a hierarchical attention mechanism to incorporate ID embeddings in modality fusing, coupled with contrastive learning, to enhance content representations. Meanwhile, we propose a lightweight graph convolution network for each modality to amalgamate neighborhood and ID embeddings for improving structural representations. Finally, the content and structure representations are combined to form the ultimate item embedding for recommendation. Extensive experiments on three real-world datasets (Baby, Sports, and Clothing) demonstrate the superiority of our method over state-of-the-art multimodal recommendation methods and the effectiveness of fine-grained ID embeddings. Our code is available at https://anonymous.4open.science/r/IDSF-code/.