FedMef: Towards Memory-efficient Federated Dynamic Pruning

arXiv:2403.14737v1 Announce Type: new
Abstract: Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train deep learning models. Neural network pruning techniques, such as dynamic pruning, could enhance model efficiency, but directly adopting them in FL still poses substantial challenges, including post-pruning performance degradation, high activation memory usage, etc. To address these challenges, we propose FedMef, a novel and memory-efficient …

abstract application arxiv computation cs.dc cs.lg data decentralized deep learning demand devices dynamic efficiency federated learning however memory network neural network pruning resources them train training type