Handling Heterophily in Recommender Systems with Wavelet Hypergraph Diffusion

2025-01-24

AI Summary

Recommender systems face challenges in modeling heterogeneous (heterophilic) user-item interactions and capturing high-order, multidimensional, and multimodal associations. Method: We propose WavHyp, a multiscale, multimodal neural network framework that jointly integrates heterophily-aware hypergraph diffusion, wavelet-domain multiscale hypergraph convolution, and a structure-text dual-channel encoder featuring multilevel clustering and intermediate/late fusion strategies. Contribution/Results: WavHyp is the first to synergistically combine these components, overcoming limitations of conventional homophily assumptions and single-scale modeling. Extensive experiments on multiple real-world datasets demonstrate that WavHyp significantly outperforms state-of-the-art methods in Recall@K and NDCG, while exhibiting superior robustness and linear scalability with respect to graph size.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Recommender systems are pivotal in delivering personalised user experiences across various domains. However, capturing the heterophily patterns and the multi-dimensional nature of user-item interactions poses significant challenges. To address this, we introduce FWHDNN (Fusion-based Wavelet Hypergraph Diffusion Neural Networks), an innovative framework aimed at advancing representation learning in hypergraph-based recommendation tasks. The model incorporates three key components: (1) a cross-difference relation encoder leveraging heterophily-aware hypergraph diffusion to adapt message-passing for diverse class labels, (2) a multi-level cluster-wise encoder employing wavelet transform-based hypergraph neural network layers to capture multi-scale topological relationships, and (3) an integrated multi-modal fusion mechanism that combines structural and textual information through intermediate and late-fusion strategies. Extensive experiments on real-world datasets demonstrate that FWHDNN surpasses state-of-the-art methods in accuracy, robustness, and scalability in capturing high-order interconnections between users and items.

Problem

• Recommendation Systems
• Sentiment Analysis
• Complex Relationships

Innovation

• FWHDNN
• Multi-modal Information Fusion
• Enhanced Recommendation Accuracy