FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare

2026-08-04

AI Summary

This work addresses the challenges of personalized and multi-objective optimization in medical federated learning, where data are non-IID, clinical objectives vary across institutions, and feature spaces only partially overlap. To tackle these issues, the authors propose a two-stage training framework: first, a Pareto-driven multi-objective federated optimization is applied over shared features to learn a common backbone model; subsequently, each client independently fine-tunes the model using its private features and local objective, achieving institution-level personalization without any additional communication overhead. This study is the first to integrate multi-objective optimization with client-side personalization in federated learning. Evaluated on the MIMIC-III and Diabetes 130-US Hospitals datasets, the proposed method significantly outperforms baselines such as FedAvg, yielding up to a 12.5% improvement in AUROC and a 32.0% reduction in MAE.

Abstract

Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. However, real-world healthcare federations are often characterised not only by non-IID data, but also by heterogeneous clinical objectives and partially overlapping feature spaces. Different hospitals may optimise distinct and potentially conflicting objectives, such as mortality risk prediction, readmission reduction, or length-of-stay estimation, while also retaining institution-specific clinical features that cannot be shared with other participants. Existing personalised FL methods mainly address statistical heterogeneity, whereas multi-objective FL approaches typically learn a shared global model without explicit client-level adaptation. To address these limitations, we propose \textbf{FedCARE}, a multi-objective personalised FL framework for smart healthcare services. FedCARE follows a two-stage training strategy. First, it learns a shared global backbone from common clinical features using Pareto-driven multi-objective federated optimisation. Second, each client independently fine-tunes the shared backbone using its private features and local clinical objectives, enabling institution-specific personalisation without additional communication overhead. We implement FedCARE in a cloud-based client-server federated deployment on the Melbourne Research Cloud and evaluate it on two real-world healthcare datasets, MIMIC-III and Diabetes 130-US Hospitals. Experimental results show that FedCARE consistently outperforms standard FL, multi-objective FL, and personalised FL baselines, achieving up to 12.5% AUROC improvement and 32.0% MAE reduction over FedAvg.

Problem

• Federated Learning
• Multi-Objective Optimization
• Personalized Learning
• Healthcare
• Non-IID Data

Innovation

• Personalized Federated Learning
• Multi-objective Optimization
• Pareto-driven FL
• Heterogeneous Features
• Smart Healthcare