PSI-PFL: Population Stability Index for Client Selection in non-IID Personalized Federated Learning
It addresses performance degradation in federated learning due to data heterogeneity, which is critical for applications requiring data privacy, but it is incremental as it builds on existing personalized federated learning approaches.
The paper tackles the problem of non-IID data in federated learning by proposing PSI-PFL, a client selection framework that uses the Population Stability Index to reduce label skew, resulting in up to 10% higher global model accuracy compared to state-of-the-art methods across multiple data types.
Federated Learning (FL) enables decentralized machine learning (ML) model training while preserving data privacy by keeping data localized across clients. However, non-independent and identically distributed (non-IID) data across clients poses a significant challenge, leading to skewed model updates and performance degradation. Addressing this, we propose PSI-PFL, a novel client selection framework for Personalized Federated Learning (PFL) that leverages the Population Stability Index (PSI) to quantify and mitigate data heterogeneity (so-called non-IIDness). Our approach selects more homogeneous clients based on PSI, reducing the impact of label skew, one of the most detrimental factors in FL performance. Experimental results over multiple data modalities (tabular, image, text) demonstrate that PSI-PFL significantly improves global model accuracy, outperforming state-of-the-art baselines by up to 10\% under non-IID scenarios while ensuring fairer local performance. PSI-PFL enhances FL performance and offers practical benefits in applications where data privacy and heterogeneity are critical.