FedTSC: A Secure Federated Learning System for Interpretable Time Series Classification

We demonstrate FedTSC, a novel federated learning (FL) system for interpretable time series classification (TSC). FedTSC is an FL-based TSC solution that makes a great balance among security, interpretability, accuracy, and efficiency. We achieve this by first extending the concept of FL to consider both stronger security and model interpretability. Then, we propose three novel TSC methods based on explainable features to deal with the challengeable FL problem. To build the model in the FL setting, we propose several security protocols that are well optimized by maximally reducing the bottlenecked communication complexity. We build the FedTSC system based on such a solution, and provide the user Sklearn-like Python APIs for practical utility. We show that the system is easy to use, and the novel TSC approach is superior.

Automated summary

We introduce FedTSC, a novel federated learning system designed for interpretable time series classification. This system achieves a great balance between security, interpretability, accuracy, and efficiency by extending the concept of federated learning, proposing novel TSC methods, and optimizing security protocols. The FedTSC system provides user-friendly Sklearn-like Python APIs and demonstrates superior performance in practical applications.