DeepAI AI Chat
Log In Sign Up

FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data

11/17/2022
by   Ming Yang, et al.
Zhejiang University
sdas.org
0

Federated learning is a distributed learning that allows each client to keep the original data locally and only upload the parameters of the local model to the server. Despite federated learning can address data island, it remains challenging to train with data heterogeneous in a real application. In this paper, we propose FedSiam-DA, a novel dual-aggregated contrastive federated learning approach, to personalize both local and global models, under various settings of data heterogeneity. Firstly, based on the idea of contrastive learning in the siamese network, FedSiam-DA regards the local and global model as different branches of the siamese network during the local training and controls the update direction of the model by constantly changing model similarity to personalize the local model. Secondly, FedSiam-DA introduces dynamic weights based on model similarity for each local model and exercises the dual-aggregated mechanism to further improve the generalization of the global model. Moreover, we provide extensive experiments on benchmark datasets, the results demonstrate that FedSiam-DA achieves outperforming several previous FL approaches on heterogeneous datasets.

READ FULL TEXT
12/06/2022

Tackling Data Heterogeneity in Federated Learning with Class Prototypes

Data heterogeneity across clients in federated learning (FL) settings is...
03/30/2021

Model-Contrastive Federated Learning

Federated learning enables multiple parties to collaboratively train a m...
03/04/2023

Federated Virtual Learning on Heterogeneous Data with Local-global Distillation

Despite Federated Learning (FL)'s trend for learning machine learning mo...
10/01/2022

Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

Federated learning aims to train models collaboratively across different...
04/08/2022

CD^2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning

Federated learning (FL) is a distributed learning paradigm that enables ...
12/20/2021

HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images

Multiple medical institutions collaboratively training a model using fed...
06/22/2022

: Calibrating Global and Local Models via Federated Learning Beyond Consensus

In federated learning (FL), the objective of collaboratively learning a ...