AI RESEARCH
A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning
arXiv CS.LG
•
ArXi:2603.22465v1 Announce Type: new Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnitude pruning effectively reduces the communication payload, it remains inherently energy-agnostic. It assumes all parameter updates incur identical downstream transmission and memory-update costs, ignoring hardware realities.