Graph-based Diffusion Model for Collaborative Filtering

2025-04-07

AI Summary

Existing diffusion-based recommendation methods treat user–item interactions as independent samples, ignoring high-order collaborative signals embedded in the user–item bipartite graph, and face two key challenges in graph diffusion: noisy heterogeneity and relational explosion. To address these, we propose the first graph diffusion recommendation framework operating directly on the bipartite graph. Our method introduces a multi-level hybrid noise corruption mechanism to jointly model continuous and discrete noise, and incorporates a user-activated sparse attention diffusion process that preserves graph topological integrity while mitigating computational overhead and noise interference. By unifying graph neural networks with diffusion modeling, our approach explicitly captures high-order connectivity. Extensive experiments on three benchmark datasets demonstrate significant improvements over state-of-the-art methods in both accuracy and diversity, validating the effectiveness and practicality of modeling high-order collaborative signals.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Recently, diffusion-based recommendation methods have achieved impressive results. However, existing approaches predominantly treat each user's historical interactions as independent training samples, overlooking the potential of higher-order collaborative signals between users and items. Such signals, which encapsulate richer and more nuanced relationships, can be naturally captured using graph-based data structures. To address this limitation, we extend diffusion-based recommendation methods to the graph domain by directly modeling user-item bipartite graphs with diffusion models. This enables better modeling of the higher-order connectivity inherent in complex interaction dynamics. However, this extension introduces two primary challenges: (1) Noise Heterogeneity, where interactions are influenced by various forms of continuous and discrete noise, and (2) Relation Explosion, referring to the high computational costs of processing large-scale graphs. To tackle these challenges, we propose a Graph-based Diffusion Model for Collaborative Filtering (GDMCF). To address noise heterogeneity, we introduce a multi-level noise corruption mechanism that integrates both continuous and discrete noise, effectively simulating real-world interaction complexities. To mitigate relation explosion, we design a user-active guided diffusion process that selectively focuses on the most meaningful edges and active users, reducing inference costs while preserving the graph's topological integrity. Extensive experiments on three benchmark datasets demonstrate that GDMCF consistently outperforms state-of-the-art methods, highlighting its effectiveness in capturing higher-order collaborative signals and improving recommendation performance.

Problem

• Model higher-order collaborative signals in user-item graphs
• Address noise heterogeneity in interaction data
• Reduce computational costs of large-scale graph processing

Innovation

• Extends diffusion models to user-item bipartite graphs
• Introduces multi-level noise corruption mechanism
• Designs user-active guided diffusion process