SOURCE-LINKED INTELLIGENCE

FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL methods typically bind training to a small predefined menu of model configurations, which limits architectural coverage. To address this bottleneck, we introduce Federated Adaptive Network Search (FANS), a hypernetwork-based framework that learns a shared architecture space rather than a fixed set of client models. To optimize this shared space efficiently, we propose the Federated Parallel Scaling (FPS) algorithm, which jointly trains multiple sa

Read original source ↗ Open in workspace

recordType

paper

region

Global