FedGraph: an Aggregation Method from Graph Perspective

10/06/2022
by   Zhifang Deng, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2022

FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning

The uneven distribution of local data across different edge devices (cli...
research
02/24/2023

FedPDC:Federated Learning for Public Dataset Correction

As people pay more and more attention to privacy protection, Federated L...
research
04/20/2021

Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation

Federated learning (FL) enables collaborative model training while prese...
research
01/30/2023

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

In federated learning (FL), the global model at the server requires an e...
research
12/14/2022

FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation

The statistical heterogeneity of the non-independent and identically dis...
research
03/23/2023

Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging

Deep learning models have shown promising performance in the field of di...
research
05/30/2023

FedDisco: Federated Learning with Discrepancy-Aware Collaboration

This work considers the category distribution heterogeneity in federated...

Please sign up or login with your details

Forgot password? Click here to reset