Don't Lose Yourself: Boosting Multimodal Recommendation via Reducing Node-neighbor Discrepancy in Graph Convolutional Network

TL;DR

This paper introduces RedN^nD, a novel GCN-based model for multimodal recommendation systems that reduces node-neighbor discrepancy to preserve personalized information and improve accuracy and robustness.

Contribution

It proposes a new method to mitigate over-smoothing in GCNs by reducing node-neighbor discrepancy, enhancing multimodal recommendation performance.

Findings

RedN^nD outperforms existing GCN-based models in accuracy.

RedN^nD demonstrates improved robustness across datasets.

The approach effectively preserves personalized node information.

Abstract

The rapid expansion of multimedia contents has led to the emergence of multimodal recommendation systems. It has attracted increasing attention in recommendation systems because its full utilization of data from different modalities alleviates the persistent data sparsity problem. As such, multimodal recommendation models can learn personalized information about nodes in terms of visual and textual. To further alleviate the data sparsity problem, some previous works have introduced graph convolutional networks (GCNs) for multimodal recommendation systems, to enhance the semantic representation of users and items by capturing the potential relationships between them. However, adopting GCNs inevitably introduces the over-smoothing problem, which make nodes to be too similar. Unfortunately, incorporating multimodal information will exacerbate this challenge because nodes that are too similar will lose the personalized information learned through multimodal information. To address this problem, we propose a novel model that retains the personalized information of ego nodes during feature aggregation by Reducing Node-neighbor Discrepancy (RedN^nD). Extensive experiments on three public datasets show that RedN^nD achieves state-of-the-art performance on accuracy and robustness, with significant improvements over existing GCN-based multimodal frameworks.