Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design

Chuan Ma, Jun Li, Ming Ding, Kang Wei, Wen Chen, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

Abstract

Owing to the low communication costs and privacypromoting capabilities, Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, with the distributed architecture, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. In this paper, we model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk. Specifically, we first investigate the impact on the models caused by unreliable clients by deriving a convergence upper bound on the loss function based on the gradient descent updates. Our theoretical bounds reveal that with a fixed amount of total computational resources, there exists an optimal number of local training iterations in terms of convergence performance. We further design a novel defensive mechanism, named deep neural network based secure aggregation (DeepSA). Our experimental results validate our theoretical analysis. In addition, the effectiveness of DeepSA is verified by comparing with other state-of-the-art defensive mechanisms.

Original languageEnglish (US)
JournalIEEE Internet of Things Journal
DOIs
StateAccepted/In press - 2021

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Keywords

  • Biological system modeling
  • Computational modeling
  • Convergence
  • Convergence bound
  • Data models
  • Defensive mechanism.
  • Federated learning
  • Hidden Markov models
  • Servers
  • Training
  • Unreliable clients

Fingerprint Dive into the research topics of 'Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design'. Together they form a unique fingerprint.

Cite this