Federated Learning with MMD-based Early Stopping for Adaptive GNSS Interference Classification
This work addresses the problem of adaptive GNSS interference classification for federated learning systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of managing novel and unbalanced data distributions in federated learning by proposing a dynamic early stopping method based on maximum mean discrepancy of feature embeddings. The result is a federated learning approach that surpasses state-of-the-art techniques in adapting to novel interference classes and multipath scenarios, as demonstrated on four GNSS datasets from real-world highways and controlled environments.
Federated learning (FL) enables multiple devices to collaboratively train a global model while maintaining data on local servers. Each device trains the model on its local server and shares only the model updates (i.e., gradient weights) during the aggregation step. A significant challenge in FL is managing the feature distribution of novel and unbalanced data across devices. In this paper, we propose an FL approach using few-shot learning and aggregation of the model weights on a global server. We introduce a dynamic early stopping method to balance out-of-distribution classes based on representation learning, specifically utilizing the maximum mean discrepancy of feature embeddings between local and global models. An exemplary application of FL is to orchestrate machine learning models along highways for interference classification based on snapshots from global navigation satellite system (GNSS) receivers. Extensive experiments on four GNSS datasets from two real-world highways and controlled environments demonstrate that our FL method surpasses state-of-the-art techniques in adapting to both novel interference classes and multipath scenarios.