Hypergraph Diffusion for High-Order Recommender Systems

TL;DR

This paper introduces WaveHDNN, a hypergraph diffusion framework that enhances high-order recommender systems by capturing heterophilic interactions and localized structures using wavelet transforms and contrastive learning.

Contribution

WaveHDNN is a novel framework combining wavelet-enhanced hypergraph diffusion with heterophily-aware encoding and multi-scale structure modeling for improved recommendations.

Findings

Outperforms existing GNN-based recommenders on benchmark datasets.

Effectively captures diverse user-item interactions and high-order relationships.

Improves recommendation accuracy by addressing over-smoothing and heterophily.

Abstract

Recommender systems rely on Collaborative Filtering (CF) to predict user preferences by leveraging patterns in historical user-item interactions. While traditional CF methods primarily focus on learning compact vector embeddings for users and items, graph neural network (GNN)-based approaches have emerged as a powerful alternative, utilizing the structure of user-item interaction graphs to enhance recommendation accuracy. However, existing GNN-based models, such as LightGCN and UltraGCN, often struggle with two major limitations: an inability to fully account for heterophilic interactions, where users engage with diverse item categories, and the over-smoothing problem in multi-layer GNNs, which hinders their ability to model complex, high-order relationships. To address these gaps, we introduce WaveHDNN, an innovative wavelet-enhanced hypergraph diffusion framework. WaveHDNN integrates a Heterophily-aware Collaborative Encoder, designed to capture user-item interactions across diverse categories, with a Multi-scale Group-wise Structure Encoder, which leverages wavelet transforms to effectively model localized graph structures. Additionally, cross-view contrastive learning is employed to maintain robust and consistent representations. Experiments on benchmark datasets validate the efficacy of WaveHDNN, demonstrating its superior ability to capture both heterophilic and localized structural information, leading to improved recommendation performance.