Saved in:
Bibliographic Details
Main Authors: Zhang, Meiying, Zhao, Huan, Ebron, Sheldon, Yang, Kan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.04409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916117512978432
author Zhang, Meiying
Zhao, Huan
Ebron, Sheldon
Yang, Kan
author_facet Zhang, Meiying
Zhao, Huan
Ebron, Sheldon
Yang, Kan
contents The performance of clients in Federated Learning (FL) can vary due to various reasons. Assessing the contributions of each client is crucial for client selection and compensation. It is challenging because clients often have non-independent and identically distributed (non-iid) data, leading to potentially noisy or divergent updates. The risk of malicious clients amplifies the challenge especially when there's no access to clients' local data or a benchmark root dataset. In this paper, we introduce a novel method called Fair, Robust, and Efficient Client Assessment (FRECA) for quantifying client contributions in FL. FRECA employs a framework called FedTruth to estimate the global model's ground truth update, balancing contributions from all clients while filtering out impacts from malicious ones. This approach is robust against Byzantine attacks and incorporates a Byzantine-resilient aggregation algorithm. FRECA is also efficient, as it operates solely on local model updates and requires no validation operations or datasets. Our experimental results show that FRECA can accurately and efficiently quantify client contributions in a robust manner.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04409
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning
Zhang, Meiying
Zhao, Huan
Ebron, Sheldon
Yang, Kan
Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
The performance of clients in Federated Learning (FL) can vary due to various reasons. Assessing the contributions of each client is crucial for client selection and compensation. It is challenging because clients often have non-independent and identically distributed (non-iid) data, leading to potentially noisy or divergent updates. The risk of malicious clients amplifies the challenge especially when there's no access to clients' local data or a benchmark root dataset. In this paper, we introduce a novel method called Fair, Robust, and Efficient Client Assessment (FRECA) for quantifying client contributions in FL. FRECA employs a framework called FedTruth to estimate the global model's ground truth update, balancing contributions from all clients while filtering out impacts from malicious ones. This approach is robust against Byzantine attacks and incorporates a Byzantine-resilient aggregation algorithm. FRECA is also efficient, as it operates solely on local model updates and requires no validation operations or datasets. Our experimental results show that FRECA can accurately and efficiently quantify client contributions in a robust manner.
title Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning
topic Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2402.04409