HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices

Excerpt

arXiv:2609.39074v1 Announce Type: new Abstract: Federated learning (FL) on memory-constrained edge devices faces a dilemma: first-order (FO) optimization (i.e., backpropagation) demands substantial memory, whereas zeroth-order (ZO) optimization suffers from severe convergence slowdown. To resolve this dilemma, we introduce HO-FL, a hybrid-order FL framework that trains a model's bottom segment with ZO optimization and its top segment with FO optimization. Each device can flexibly select its orde