ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning

TL;DR

This paper introduces ASMR, a new method for robust federated learning that dynamically detects and excludes malfunctioning clients without prior knowledge or hyperparameters, improving model resilience.

Contribution

The paper presents ASMR, a hyperparameter-free, dynamic approach for identifying malfunctioning clients in federated learning based on angular distance, enhancing robustness against various issues.

Findings

ASMR effectively detects malfunctioning clients in image classification tasks.

Dynamic adaptation of decision boundaries improves detection accuracy.

ASMR outperforms existing methods in resilience without needing prior knowledge.

Abstract

Federated Learning (FL) allows the training of deep neural networks in a distributed and privacy-preserving manner. However, this concept suffers from malfunctioning updates sent by the attending clients that cause global model performance degradation. Reasons for this malfunctioning might be technical issues, disadvantageous training data, or malicious attacks. Most of the current defense mechanisms are meant to require impractical prerequisites like knowledge about the number of malfunctioning updates, which makes them unsuitable for real-world applications. To counteract these problems, we introduce a novel method called Angular Support for Malfunctioning Client Resilience (ASMR), that dynamically excludes malfunctioning clients based on their angular distance. Our novel method does not require any hyperparameters or knowledge about the number of malfunctioning clients. Our experiments showcase the detection capabilities of ASMR in an image classification task on a histopathological dataset, while also presenting findings on the significance of dynamically adapting decision boundaries.