aiqbench analysis
FedPCD introduces a novel optimization framework for federated learning that balances global model accuracy with fairness constraints for heterogeneous clients without altering the standard aggregation direction. By minimizing necessary corrections to meet performance thresholds, the method achieves superior worst-case client accuracy and faster convergence compared to existing state-of-the-art baselines. This work advances the theoretical and practical limits of distributed machine learning under data heterogeneity.
FedPCD: Priority-Constrained Federated Aggregation
arXiv:2610.13508v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2610.13508 [cs.LG]
(or arXiv:2610.13508v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.13508 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 249 words
Related coverage
A Red Line and Oversight Framework for Government AI Contracts
AI Alignment Forum · Jul 18, 2026
Constrained Bayesian Optimization for Hierarchical Federated Learning in IoT Networks for Plant Disease Classification
arXiv · Sep 9, 2026
A Locally Penalized Cross-Estimate Federated Method with Guarantees for Constrained Personalized Learning
arXiv · Oct 5, 2026
Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs
arXiv · Oct 15, 2026