Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning
This work addresses the problem of biased updates and degraded performance in federated learning for applications with non-IID data, offering a lightweight clustering solution that improves accuracy and fairness, though it is incremental as it builds on existing FL and clustering methods.
The paper tackles performance degradation in federated learning due to non-IID data by proposing Clust-PSI-PFL, a clustering-based personalized FL framework that uses a weighted Population Stability Index (PSI) to quantify data skew and group clients, achieving up to 18% higher global accuracy and 37% relative improvement in client fairness across diverse datasets and protocols.
Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $α$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew.