FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ceyani, Emir, Xie, Han, Buyukates, Baturalp, Yang, Carl, Avestimehr, Salman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915117391675392
author Ceyani, Emir
Xie, Han
Buyukates, Baturalp
Yang, Carl
Avestimehr, Salman
author_facet Ceyani, Emir
Xie, Han
Buyukates, Baturalp
Yang, Carl
Avestimehr, Salman
contents 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 \textit{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 \textit{FedGrAINS} as a regularizer consistently improves the FL performance compared to baselines that do not leverage such regularization.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
Ceyani, Emir
Xie, Han
Buyukates, Baturalp
Yang, Carl
Avestimehr, Salman
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Information Retrieval
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 \textit{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 \textit{FedGrAINS} as a regularizer consistently improves the FL performance compared to baselines that do not leverage such regularization.
title FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Information Retrieval
url https://arxiv.org/abs/2501.12592