Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Auto-Weighted Robust Federated Learning with Corrupted Data Sources
Uppsala University, Sweden.
University of Hong Kong, China.
University College London, UK.
RISE Research Institutes of Sweden, Digital Systems, Data Science. Uppsala University, Sweden.ORCID iD: 0000-0002-2586-8573
2022 (English)In: ACM Transactions on Intelligent Systems and Technology, ISSN 2157-6904, E-ISSN 2157-6912, Vol. 13, no 5Article in journal (Refereed) Published
Abstract [en]

Federated learning provides a communication-efficient and privacy-preserving training process by enabling learning statistical models with massive participants without accessing their local data. Standard federated learning techniques that naively minimize an average loss function are vulnerable to data corruptions from outliers, systematic mislabeling, or even adversaries. In this article, we address this challenge by proposing Auto-weighted Robust Federated Learning (ARFL), a novel approach that jointly learns the global model and the weights of local updates to provide robustness against corrupted data sources. We prove a learning bound on the expected loss with respect to the predictor and the weights of clients, which guides the definition of the objective for robust federated learning. We present an objective that minimizes the weighted sum of empirical risk of clients with a regularization term, where the weights can be allocated by comparing the empirical risk of each client with the average empirical risk of the best ( p ) clients. This method can downweight the clients with significantly higher losses, thereby lowering their contributions to the global model. We show that this approach achieves robustness when the data of corrupted clients is distributed differently from the benign ones. To optimize the objective function, we propose a communication-efficient algorithm based on the blockwise minimization paradigm. We conduct extensive experiments on multiple benchmark datasets, including CIFAR-10, FEMNIST, and Shakespeare, considering different neural network models. The results show that our solution is robust against different scenarios, including label shuffling, label flipping, and noisy features, and outperforms the state-of-the-art methods in most scenarios.

Place, publisher, year, edition, pages
Association for Computing Machinery , 2022. Vol. 13, no 5
Keywords [en]
Federated learning, robustness, Auto-weighted, distributed learning, neural networks
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:ri:diva-59799DOI: 10.1145/3517821OAI: oai:DiVA.org:ri-59799DiVA, id: diva2:1683126
Available from: 2022-07-14 Created: 2022-07-14 Last updated: 2023-06-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full texthttps://doi.org/10.1145/3517821

Authority records

Voigt, Thiemo

Search in DiVA

By author/editor
Voigt, Thiemo
By organisation
Data Science
In the same journal
ACM Transactions on Intelligent Systems and Technology
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 45 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf