FedGraph: an Aggregation Method from Graph Perspective

2022-10-06 · Zhifang Deng, Xiaohong Huang, Dandan Li, Xueguang Yuan

With the increasingly strengthened data privacy act and the difficult data centralization, Federated Learning (FL) has become an effective solution to collaboratively train the model while preserving each client's privacy. FedAvg is a standard aggregation algorithm that makes the proportion of dataset size of each client as aggregation weight. However, it can't deal with non-independent and identically distributed (non-i.i.d) data well because of its fixed aggregation weights and the neglect of data distribution. In this paper, we propose an aggregation strategy that can effectively deal with non-i.i.d dataset, namely FedGraph, which can adjust the aggregation weights adaptively according to the training condition of local models in whole training process. The FedGraph takes three factors into account from coarse to fine: the proportion of each local dataset size, the topology factor of model graphs, and the model weights. We calculate the gravitational force between local models by transforming the local models into topology graphs. The FedGraph can explore the internal correlation between local models better through the weighted combination of the proportion each local dataset, topology structure, and model weights. The proposed FedGraph has been applied to the MICCAI Federated Tumor Segmentation Challenge 2021 (FeTS) datasets, and the validation results show that our method surpasses the previous state-of-the-art by 2.76 mean Dice Similarity Score. The source code will be available at Github.

📄 PDF Abstract BibTeX arXiv:2210.02733

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning Tumor Segmentation

FedGraph: Federated Graph Learning with Intelligent Sampling

2021-11-02 · Fahao Chen, Peng Li, Toshiaki Miyazaki, Celimuge Wu

Federated learning has attracted much research attention due to its privacy protection in distributed machine learning. However, existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), w…

Deep Reinforcement Learning Federated Learning Graph Learning Graph Sampling

FedGraph: A Research Library and Benchmark for Federated Graph Learning

2024-10-08 · Yuhang Yao, Yuan Li, Xinyi Fan, Junhao Li 외

Federated graph learning is an emerging field with significant practical challenges. While algorithms have been proposed to improve the accuracy of training graph neural networks, such as node classification on federated…

Benchmarking Federated Learning Graph Learning Node Classification

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks

2021-04-14 · Chaoyang He, Keshav Balasubramanian, Emir Ceyani, Carl Yang 외

Graph Neural Network (GNN) research is rapidly growing thanks to the capacity of GNNs in learning distributed representations from graph-structured data. However, centralizing a massive amount of real-world graph data fo…

Federated Learning Graph Neural Network Molecular Property Prediction

Federated Graph AGI for Cross-Border Insider Threat Intelligence in Government Financial Schemes

2026-02-18 · Srikumar Nayak, James Walmesley arxiv

Cross-border insider threats pose a critical challenge to government financial schemes, particularly when dealing with distributed, privacy-sensitive data across multiple jurisdictions. Existing approaches face fundament…

Federated Learning Causal Inference Graph Learning

FedGraph-VASP: Privacy-Preserving Federated Graph Learning with Post-Quantum Security for Cross-Institutional Anti-Money Laundering

2026-01-25 · Daniel Commey, Matilda Nkoom, Yousef Alsenani, Sena G. Hounsinou 외 arxiv

Virtual Asset Service Providers (VASPs) face a fundamental tension between regulatory compliance and user privacy when detecting cross-institutional money laundering. Current approaches require either sharing sensitive t…

Graph Neural Network Fraud Detection Graph Learning