FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning

05/03/2022
by   SangMook Kim, et al.
0

Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels. However, it is far more complex and challenging owing to varying levels of data heterogeneity and noise over clients, which exacerbates the client-to-client performance discrepancy. In this work, we propose a robust federated learning method called FedRN, which exploits k-reliable neighbors with high data expertise or similarity. Our method helps mitigate the gap between low- and high-performance clients by training only with a selected set of clean examples, identified by their ensembled mixture models. We demonstrate the superiority of FedRN via extensive evaluations on three real-world or synthetic benchmark datasets. Compared with existing robust training methods, the results show that FedRN significantly improves the test accuracy in the presence of noisy labels.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/10/2022

FedCorr: Multi-Stage Federated Learning for Label Noise Correction

Federated learning (FL) is a privacy-preserving distributed learning par...
07/09/2020

Client Adaptation improves Federated Learning with Simulated Non-IID Clients

We present a federated learning approach for learning a client adaptable...
06/04/2021

FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning

Client contribution evaluation, also known as data valuation, is a cruci...
01/22/2020

Data Selection for Federated Learning with Relevant and Irrelevant Data at Clients

Federated learning is an effective way of training a machine learning mo...
10/27/2021

What Do We Mean by Generalization in Federated Learning?

Federated learning data is drawn from a distribution of distributions: c...
05/20/2022

FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels

Federated learning (FL) aims at training a global model on the server si...
06/20/2021

Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning

Shapley Value is commonly adopted to measure and incentivize client part...