Multi-View Graph Convolutional Network for Multimedia Recommendation

Abstract

Multimedia recommendation has received much attention in recent years. It models user preferences based on both behavior information and item multimodal information. Though current GCN-based methods achieve notable success, they suffer from two limitations: (1) Modality noise contamination to the item representations. Existing methods often mix modality features and behavior features in a single view (e.g., user-item view) for propagation, the noise in the modality features may be amplified and coupled with behavior features. In the end, it leads to poor feature discriminability; (2) Incomplete user preference modeling caused by equal treatment of modality features. Users often exhibit distinct modality preferences when purchasing different items. Equally fusing each modality feature ignores the relative importance among different modalities, leading to the suboptimal user preference modeling. To tackle the above issues, we propose a novel Multi-View Graph Convolutional Network for the multimedia recommendation. Specifically, to avoid modality noise contamination, the modality features are first purified with the aid of item behavior information. Then, the purified modality features of items and behavior features are enriched in separate views, including the user-item view and the item-item view. In this way, the distinguishability of features is enhanced. Meanwhile, a behavior-aware fuser is designed to comprehensively model user preferences by adaptively learning the relative importance of different modality features. Furthermore, we equip the fuser with a self-supervised auxiliary task. This task is expected to maximize the mutual information between the fused multimodal features and behavior features, so as to capture complementary and supplementary preference information simultaneously. Extensive experiments on three public datasets demonstrate the effectiveness of our methods.

arXiv commentMM'23

References in corpus (16)

• Neural Graph Collaborative Filtering
• Learning deep representations by mutual information estimation and maximization
• Simplifying Graph Convolutional Networks
• Language Modeling with Gated Convolutional Networks
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Mining Latent Structures for Multimedia Recommendation
• Bootstrap Latent Representations for Multi-modal Recommendation
• Multi-Modal Self-Supervised Learning for Recommendation
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Graph Neural Networks in Recommender Systems: A Survey
• MMRec: Simplifying Multimodal Recommendation
• M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering

Cited by in corpus (7)

• Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation
• Formalizing Multimedia Recommendation through Multimodal Deep Learning
• Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising
• RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation
• Causality-Inspired Fair Representation Learning for Multimodal Recommendation
• Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation
• I${}^3$-MRec: Invariant Learning with Information Bottleneck for Incomplete Modality Recommendation