Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
FedPCD introduces a priority-constrained federated optimization framework that decouples global model aggregation from client fairness objectives. By preserving the standard federated aggregate as the primary goal and applying minimal corrections to satisfy client performance constraints, FedPCD achieves superior global accuracy and improved worst-10% client accuracy on heterogeneous benchmarks. Furthermore, FedPCD demonstrates faster convergence, reaching comparable or better performance in fewer communication rounds.
Prioritizing global accuracy while minimally correcting for client fairness unlocks state-of-the-art performance and faster convergence in federated learning.
Federated learning (FL) seeks to optimize a shared global model from decentralized client data. While effective for average performance, this process can produce unfair performance across clients, particularly under statistically heterogeneous data distributions. Existing fairness-aware and multi-objective FL methods address this through client re-weighting, gradient correction, or common-descent formulations, but often change the global optimization direction or treat client objectives symmetrically. We propose FedPCD, a priority-constrained federated optimization framework that separates the global optimization objective from client protection. FedPCD preserves the conventional federated aggregate as the primary objective, while allowing only the minimum correction necessary to meet client performance constraints. Across heterogeneous FL benchmarks, FedPCD consistently outperforms state-of-the-art baselines, achieving the highest global accuracy across all configurations and leading worst-10% client accuracy in nearly all. FedPCD further preserves competitive trade-offs between global accuracy and client performance variability. Beyond this trade-off, FedPCD demonstrates faster empirical convergence, reaching matching or superior performance in substantially fewer communication rounds.