Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation

2024-08-01

arXiv.org

AI Summary

To address the degradation of graph neural recommendation models under distributional shifts (out-of-distribution, OOD), this paper proposes CausalDiffRec, a causal diffusion-based recommendation framework. It constructs a structural causal model to identify environmental confounders, pioneers the integration of causal inference with diffusion models, implements backdoor adjustment for environment distribution inversion, and introduces a variational counterfactual deconfounding mechanism—rigorously proven to learn environment-invariant graph representations. Evaluated on Food, KuaiRec, Yelp2018, and Douban, CausalDiffRec achieves average improvements of 10.69%–22.41% under OOD settings, significantly enhancing recommendation robustness and cross-environment generalization. Key contributions include: (1) joint causal-diffusion modeling; (2) a falsifiable paradigm for learning environment-invariant representations; and (3) an operationalizable backdoor adjustment design tailored for recommender systems.

Technology Category

• Machine Learning: Causal Learning
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Causality

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. However, this assumption often fails in the presence of out-of-distribution (OOD) data, resulting in significant performance degradation. In this study, we construct a Structural Causal Model (SCM) to analyze interaction data, revealing that environmental confounders (e.g., the COVID-19 pandemic) lead to unstable correlations in GNN-based models, thus impairing their generalization to OOD data. To address this issue, we propose a novel approach, graph representation learning via causal diffusion (CausalDiffRec) for OOD recommendation. This method enhances the model's generalization on OOD data by eliminating environmental confounding factors and learning invariant graph representations. Specifically, we use backdoor adjustment and variational inference to infer the real environmental distribution, thereby eliminating the impact of environmental confounders. This inferred distribution is then used as prior knowledge to guide the representation learning in the reverse phase of the diffusion process to learn the invariant representation. In addition, we provide a theoretical derivation that proves optimizing the objective function of CausalDiffRec can encourage the model to learn environment-invariant graph representations, thereby achieving excellent generalization performance in recommendations under distribution shifts. Our extensive experiments validate the effectiveness of CausalDiffRec in improving the generalization of OOD data, and the average improvement is up to 10.69% on Food, 18.83% on KuaiRec, 22.41% on Yelp2018, and 11.65% on Douban datasets.

Problem

• Graph Neural Networks
• Recommendation Algorithm
• COVID-19 Impact

Innovation

• CausalDiffRec
• Cross-environment Recommendation
• COVID-19 Impact Mitigation