Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
This work addresses the under-parameterization bottleneck for bandwidth-constrained clients in heterogeneous federated learning, offering a practical solution that improves both convergence and final accuracy.
FedGMR introduces Gradual Model Restoration to progressively increase sub-model density for bandwidth-constrained clients in model-heterogeneous federated learning, achieving faster convergence and up to 10% higher accuracy on benchmarks like CIFAR-10 and ImageNet-100 under severe heterogeneity.
Federated learning (FL) enables distributed model training, yet in heterogeneous deployments, Bandwidth-Constrained Clients (BCCs) often contribute inefficiently due to limited uplink bandwidth. In model-heterogeneous FL with fixed small sub-models, BCCs may improve quickly in early rounds but become under-parameterized later, resulting in slow convergence and poor generalization. To address this challenge, we propose FedGMR, a federated learning framework centered around Gradual Model Restoration (GMR), where GMR progressively increases each client's sub-model density during training, allowing BCCs to remain effective contributors throughout optimization. To make GMR practical under real-world heterogeneity, FedGMR is realized as an end-to-end workflow with asynchronous coordination and stable, mask-aware aggregation. We further establish convergence guarantees, showing that the aggregation error scales with the average sub-model density across clients and rounds, and that GMR provably narrows the gap toward full-model FL. Extensive experiments on FEMNIST, CIFAR-10, ImageNet-100, and StackOverflow demonstrate that FedGMR improves both convergence speed and final accuracy, especially under severe heterogeneity and non-IID data distributions.