AI4S News · AI and science frontiers

arXiv Oct 12, 2026

Federated learning stops trading away tail clients: keep the FedAvg direction, correct only what client constraints require

Federated aggregation no longer rewrites the global optimization direction to gain fairness. Earlier methods reweight clients, correct conflicting gradients, or treat client losses as symmetric multi-objective common descent, all of which change the global update direction. FedPCD keeps the conventional FedAvg aggregate as the primary objective and individual client updates as secondary constraints, applying only the minimum correction needed when a constraint is violated; across CIFAR-10, CIFAR-100 and Fashion-MNIST it reaches the highest global accuracy in all 18 configurations and the highest worst-10% client accuracy in 17 of them.

American University of Sharjah

Yousef Irshaid（First author）

FedPCD Priority-Constrained Descent Federated Learning Multi-Objective Optimization

PCD pins the primary gradient into the update direction and holds 70.9% accuracy at 90% sparsity on ResNet-34/CIFAR-100 while symmetric multi-objective baselines collapse

The work introduces Priority-Constrained Descent (PCD), a gradient-based framework that anchors on the primary gradient and applies only the minimal Euclidean distortion needed to guarantee each secondary objective a τ-fraction of first-order progress, reporting better per-objective performance and Pareto dominance over symmetric multi-objective methods in structured pruning, unstructured sparsity with low-rankness, and synthetic experiments, with closed-form solutions for two and three objectives and scale invariance.