<ul data-eligibleForWebStory="false"><li>Recent studies in federated learning (FL) have focused on static datasets, but in real-world scenarios, data often arrives in streams with shifting distributions, leading to concept drift and performance degradation.</li><li>A new paper presents an information-theoretic analysis of FL performance under concept drift, introducing the concept of Stationary Generalization Error to evaluate a model's ability to capture characteristics of future unseen data.</li><li>The paper models concept drift as a Markov chain and proposes an algorithm that incorporates KL divergence and mutual information to mitigate performance degradation caused by drift patterns like periodic, gradual, and random changes in data distribution.</li><li>Experimental results using a Raspberry Pi4 FL testbed validate the proposed algorithm, showing improved performance over existing approaches in adapting to concept drift, highlighting the importance of considering shifting data distributions in FL.</li></ul>

An Information-Theoretic Analysis for Federated Learning under Concept Drift

Discover more