FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling

2025-01-22

AI Summary

To address unstable personalized GNN training in graph federated learning caused by client subgraph heterogeneity (e.g., divergent node-degree distributions), this paper proposes the first framework integrating Generative Flow Networks (GFlowNets) into subgraph federated learning. Our method enables task-aware node importance estimation and dynamically adapts message-passing steps and neighbor-sampling radius accordingly, ensuring both privacy preservation and regulatory compliance. Through trajectory-balancing optimization, the model achieves an average accuracy improvement of 3.2–5.8% over unregularized baselines across multiple graph federated learning benchmarks, while significantly accelerating convergence and enhancing robustness. The core contribution lies in the first application of GFlowNets to adaptive, structure-aware modeling in federated graph learning—establishing a novel, interpretable, and optimizable paradigm for personalized GNN training on heterogeneous subgraphs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

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

Abstract

Graphs are crucial for modeling relational and biological data. As datasets grow larger in real-world scenarios, the risk of exposing sensitive information increases, making privacy-preserving training methods like federated learning (FL) essential to ensure data security and compliance with privacy regulations. Recently proposed personalized subgraph FL methods have become the de-facto standard for training personalized Graph Neural Networks (GNNs) in a federated manner while dealing with the missing links across clients' subgraphs due to privacy restrictions. However, personalized subgraph FL faces significant challenges due to the heterogeneity in client subgraphs, such as degree distributions among the nodes, which complicate federated training of graph models. To address these challenges, we propose extit{FedGrAINS}, a novel data-adaptive and sampling-based regularization method for subgraph FL. FedGrAINS leverages generative flow networks (GFlowNets) to evaluate node importance concerning clients' tasks, dynamically adjusting the message-passing step in clients' GNNs. This adaptation reflects task-optimized sampling aligned with a trajectory balance objective. Experimental results demonstrate that the inclusion of extit{FedGrAINS} as a regularizer consistently improves the FL performance compared to baselines that do not leverage such regularization.

Problem

• Federated Learning
• Graph Neural Networks
• Personalization

Innovation

• FedGrAINS
• GFlowNets
• Dynamic Adjustment