# Federated Learning for Feature Generalization with Convex Constraints Source: [Federated Learning for Feature Generalization with Convex Constraints]() Collection index: [llms.txt]() Data updated: 2026-06-16T05:00:05.515Z Authors: Dongwon Kim, Donghee Kim, Sung Kuk Shyn, Kwangsu Kim Published: 2026-06-12T12:50:33.000Z ## Abstract Federated learning (FL) often struggles with generalization due to heterogeneous client data. Local models are prone to overfitting their local data distributions, and even transferable features can be distorted during aggregation. To address these challenges, we propose FedCONST, an approach that adaptively modulates update magnitudes based on the parameter strength of the global model. This prevents over-emphasizing well-learned parameters while reinforcing underdeveloped ones. Specifically, FedCONST employs linear convex constraints to ensure training stability and preserve locally learned generalization capabilities during aggregation. A Gradient Signal to Noise Ratio (GSNR) analysis further validates the effectiveness of FedCONST in enhancing feature transferability and robustness. As a result, FedCONST effectively aligns local and global objectives, mitigating overfitting and promoting stronger generalization across diverse FL environments, achieving state-of-the-art performance. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 Cross-Device alpha=0.5](): Image Classification; CIFAR-10 Cross-Device alpha=0.5; Top-1 Accuracy: 66.94. - [Image Classification on CIFAR-10 Cross-Silo (alpha=0.2)](): Image Classification; CIFAR-10 Cross-Silo, alpha=0.2; Top-1 Accuracy: 68.87. - [Image Classification on CIFAR-10 Cross-Silo (alpha=0.5)](): Image Classification; CIFAR-10 Cross-Silo, alpha=0.5; Top-1 Accuracy: 75.09. - [Image Classification on CIFAR-100 Cross-Silo, alpha=0.5](): Image Classification; CIFAR-100 Cross-Silo, alpha=0.5; Top-1 Accuracy: 39.61. ## Original sources and implementation [Original paper]() [PDF]()