Invariance Matters: Empowering Social Recommendation via Graph Invariant Learning

• URL: http://arxiv.org/abs/2504.10432v2
• Date: Sun, 27 Apr 2025 13:30:07 GMT
• Title: Invariance Matters: Empowering Social Recommendation via Graph Invariant Learning
• Authors: Yonghui Yang, Le Wu, Yuxin Liao, Zhuangzhuang He, Pengyang Shao, Richang Hong, Meng Wang,
• Abstract summary: Social Graph Invariant Learning (SGIL) aims to uncover stable user preferences within the input social graph.<n>To achieve this goal, SGIL first simulates multiple noisy social environments through graph generators.<n>To further promote diversity in the generated social environments, we employ an adversarial training strategy.
• Score: 39.957513241513105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph-based social recommendation systems have shown significant promise in enhancing recommendation performance, particularly in addressing the issue of data sparsity in user behaviors. Typically, these systems leverage Graph Neural Networks (GNNs) to capture user preferences by incorporating high-order social influences from observed social networks. However, existing graph-based social recommendations often overlook the fact that social networks are inherently noisy, containing task-irrelevant relationships that can hinder accurate user preference learning. The removal of these redundant social relations is crucial, yet it remains challenging due to the lack of ground truth. In this paper, we approach the social denoising problem from the perspective of graph invariant learning and propose a novel method, Social Graph Invariant Learning(SGIL). Specifically,SGIL aims to uncover stable user preferences within the input social graph, thereby enhancing the robustness of graph-based social recommendation systems. To achieve this goal, SGIL first simulates multiple noisy social environments through graph generators. It then seeks to learn environment-invariant user preferences by minimizing invariant risk across these environments. To further promote diversity in the generated social environments, we employ an adversarial training strategy to simulate more potential social noisy distributions. Extensive experimental results demonstrate the effectiveness of the proposed SGIL. The code is available at https://github.com/yimutianyang/SIGIR2025-SGIL.

Related papers

• Contrastive Learning Augmented Social Recommendations [9.20712944489791]
  We propose leveraging reconstructed social graph to complement interest representations derived from behavioral data.<n>Despite the widespread availability of social graphs on content platforms, their utility is hindered by social-relation noise.<n>We introduce a dual-view denoising framework to mitigate noise propagation in graph data and extract reliable social interests.
  arXiv  Detail & Related papers  (2025-01-03T16:29:51Z)
• Score-based Generative Diffusion Models for Social Recommendations [24.373323217763634]
  The effectiveness of social recommendations largely relies on the social homophily assumption. In this paper, we tackle the low social homophily challenge from an innovative generative perspective.
  arXiv  Detail & Related papers  (2024-12-20T05:23:45Z)
• Graph Bottlenecked Social Recommendation [47.83350026188183]
  We propose a novel Graph Bottlenecked Social Recommendation (GBSR) framework to tackle the social noise issue. GBSR is a model-agnostic social denoising framework, that aims to maximize the mutual information between the denoised social graph and recommendation labels.
  arXiv  Detail & Related papers  (2024-06-12T13:44:22Z)
• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias [64.73474454254105]
  Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. Existing social recommendation models fail to address the issues of popularity bias and the redundancy of social information. We propose a Condition-Guided Social Recommendation Model (named CGSoRec) to mitigate the model's popularity bias.
  arXiv  Detail & Related papers  (2024-05-27T02:45:01Z)
• Learning Social Graph for Inactive User Recommendation [50.090904659803854]
  LSIR learns an optimal social graph structure for social recommendation, especially for inactive users. Experiments on real-world datasets demonstrate that LSIR achieves significant improvements of up to 129.58% on NDCG in inactive user recommendation.
  arXiv  Detail & Related papers  (2024-05-08T03:40:36Z)
• Federated Social Recommendation with Graph Neural Network [69.36135187771929]
  We propose fusing social information with user-item interactions to alleviate it, which is the social recommendation problem. We devise a novel framework textbfFedrated textbfSocial recommendation with textbfGraph neural network (FeSoG)
  arXiv  Detail & Related papers  (2021-11-21T09:41:39Z)
• Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks [29.82196381724099]
  We propose a new Social Recommendation framework with Hierarchical Graph Neural Networks (SR-HGNN) In particular, we first design a relation-aware reconstructed graph neural network to inject the cross-type collaborative semantics into the recommendation framework. In addition, we further augment SR-HGNN with a social relation encoder based on the mutual information learning paradigm between low-level user embeddings and high-level global representation.
  arXiv  Detail & Related papers  (2021-10-08T11:26:04Z)
• Graph-Based Social Relation Reasoning [101.9402771161935]
  We propose a graph relational reasoning network (GR2N) for social relation recognition. Our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Experimental results illustrate that our method generates a reasonable and consistent social relation graph.
  arXiv  Detail & Related papers  (2020-07-15T03:01:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.