Concept drift detection and adaptation for federated and continual learning

Abstract

Smart devices, such as smartphones, wearables, robots, and others, can collect vast amounts of data from their environment. This data is suitable for training machine learning models, which can significantly improve their behavior, and therefore, the user experience. Federated learning is a young and popular framework that allows multiple distributed devices to train deep learning models collaboratively while preserving data privacy. Nevertheless, this approach may not be optimal for scenarios where data distribution is non-identical among the participants or changes over time, causing what is known as concept drift. Little research has yet been done in this field, but this kind of situation is quite frequent in real life and poses new challenges to both continual and federated learning. Therefore, in this work, we present a new method, called Concept-Drift-Aware Federated Averaging (CDA-FedAvg). Our proposal is an extension of the most popular federated algorithm, Federated Averaging (FedAvg), enhancing it for continual adaptation under concept drift. We empirically demonstrate the weaknesses of regular FedAvg and prove that CDA-FedAvg outperforms it in this type of scenario.

References in corpus (12)

• Federated Learning: Challenges, Methods, and Future Directions
• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Learning with Non-IID Data
• Federated Learning for Mobile Keyboard Prediction
• Learning under Concept Drift: A Review
• Federated Optimization:Distributed Optimization Beyond the Datacenter
• Three scenarios for continual learning
• Characterizing Concept Drift
• Federated Optimization in Heterogeneous Networks
• Adaptive Personalized Federated Learning
• LEAF: A Benchmark for Federated Settings
• Federated Continual Learning with Weighted Inter-client Transfer

Cited by in corpus (5)

• Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches
• FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging
• Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
• Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning
• Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data