Federated Continual Graph Learning

2024-11-28 · Yinlin Zhu, Miao Hu, Di wu

Managing evolving graph data presents substantial challenges in storage and privacy, and training graph neural networks (GNNs) on such data often leads to catastrophic forgetting, impairing performance on earlier tasks. Despite existing continual graph learning (CGL) methods mitigating this to some extent, they rely on centralized architectures and ignore the potential of distributed graph databases to leverage collective intelligence. To this end, we propose Federated Continual Graph Learning (FCGL) to adapt GNNs across multiple evolving graphs under storage and privacy constraints. Our empirical study highlights two core challenges: local graph forgetting (LGF), where clients lose prior knowledge when adapting to new tasks, and global expertise conflict (GEC), where the global GNN exhibits sub-optimal performance in both adapting to new tasks and retaining old ones, arising from inconsistent client expertise during server-side parameter aggregation. To address these, we introduce POWER, a framework that preserves experience nodes with maximum local-global coverage locally to mitigate LGF, and leverages pseudo-prototype reconstruction with trajectory-aware knowledge transfer to resolve GEC. Experiments on various graph datasets demonstrate POWER's superiority over federated adaptations of CGL baselines and vision-centric federated continual learning approaches.

📄 PDF Abstract BibTeX arXiv:2411.18919

Code (1)

zyl24/fcgl_power 공식 구현 pytorch

Tasks

Continual Learning Graph Learning Transfer Learning

Federated Continual Learning with Weighted Inter-client Transfer

2020-03-06 · Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang 외

There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where…

Continual Learning Federated Learning Transfer Learning

A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions

2023-06-03 · Hao Wang, Ruihong He, XiaoYu Zhang, Zhaoying Bian 외

Deep learning techniques have been widely used in computed tomography (CT) but require large data sets to train networks. Moreover, data sharing among multiple institutions is limited due to data privacy constraints, whi…

Computed Tomography (CT)Continual Learning Federated Learning

Federated Continual Learning for Privacy-Preserving Hospital Imaging Classification

2026-01-11 · Anay Sinhal, Arpana Sinhal, Amit Sinhal arxiv

Deep learning models for radiology interpretation increasingly rely on multi-institutional data, yet privacy regulations and distribution shift across hospitals limit central data pooling. Federated learning (FL) allows …

Federated Learning Continual Learning

Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory

2023-09-07 · Naoki Masuyama, Yusuke Nojima, Yuichiro Toda, Chu Kiong Loo 외

With the increasing importance of data privacy protection, various privacy-preserving machine learning methods have been proposed. In the clustering domain, various algorithms with a federated learning framework (i.e., f…

Clustering Continual Learning Federated Learning Privacy Preserving

Addressing Client Drift in Federated Continual Learning with Adaptive Optimization

2022-03-24 · Yeshwanth Venkatesha, Youngeun Kim, Hyoungseob Park, Yuhang Li 외

Federated learning has been extensively studied and is the prevalent method for privacy-preserving distributed learning in edge devices. Correspondingly, continual learning is an emerging field targeted towards learning …

Continual Learning Federated Learning Privacy Preserving