ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning
This addresses the issue of unreliable client updates in Federated Learning for privacy-sensitive applications, offering a practical defense without impractical prerequisites, though it is incremental as it builds on existing angular distance concepts.
The paper tackles the problem of malfunctioning client updates degrading global model performance in Federated Learning by introducing ASMR, a method that dynamically excludes such clients based on angular distance without requiring hyperparameters or prior knowledge, achieving effective detection in image classification on a histopathological dataset.
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.