paper-with-me

홈 › Papers

FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity

2025-01-01 · CVPR 2025 1 · Zihan Tan, Guancheng Wan, Wenke Huang, He Li, Guibin Zhang, Carl Yang, Mang Ye

Federated Graph Learning (FGL) has emerged as a solution to address real-world privacy concerns and data silos in graph learning, which relies on Graph Neural Networks (GNNs). Nevertheless, the homophily level discrepancies within the local graph data of clients, termed homophily heterogeneity, significantly degrade the generalizability of a global GNN. Existing research ignores this issue and suffers from unpromising collaboration. In this paper, we propose FedSPA, an effective framework that addresses homophily heterogeneity from the perspectives of homophily conflict and homophily bias. In the first place, the homophily conflict arises when training on inconsistent homophily levels across clients. Correspondingly, we propose Subgraph Feature Propagation Decoupling (SFPD), thereby achieving collaboration on unified homophily levels across clients. To further address homophily bias, we design Homophily Bias-Driven Aggregation (HBDA) which emphasizes clients with lower biases. It enables the adaptive adjustment of each client contribution to the global GNN based on its homophily bias. The superiority of FedSPA is validated through extensive experiments. The code is available at https://github.com/OakleyTan/FedSPA.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

FedSpaLLM: Federated Pruning of Large Language Models

2024-10-18 · Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao 외

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. Pruning can reduce model size, yet existing methods assume public acces…

Federated LearningPrivacy Preserving

FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning

2025-11-05 · Chaimaa Medjadji, Sadi Alawadi, Feras M. Awaysheh, Guilain Leduc 외 arxiv

Federated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy by keeping raw data local. However, FL suffers from significant communication overhead due to the fr…

Federated Learning

Achieving Personalized Federated Learning with Sparse Local Models

2022-01-27 · Tiansheng Huang, Shiwei Liu, Li Shen, Fengxiang He 외

Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL)…

Federated LearningPersonalized Federated Learning

On Heterogeneously Distributed Data, Sparsity Matters

2021-09-29 · Tiansheng Huang, Shiwei Liu, Li Shen, Fengxiang He 외

Federated learning (FL) is particularly vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personal…

Federated LearningPersonalized Federated Learning

Asynchronous Federated Continual Learning

2023-04-07 · Donald Shenaj, Marco Toldo, Alberto Rigon, Pietro Zanuttigh

The standard class-incremental continual learning setting assumes a set of tasks seen one after the other in a fixed and predefined order. This is not very realistic in federated learning environments where each client w…

Continual LearningFederated Learning