Dual-Segment Clustering Strategy for Federated Learning in Heterogeneous Environments

arXiv:2405.09276v1 Announce Type: new
Abstract: Federated learning (FL) is a distributed machine learning paradigm with high efficiency and low communication load, only transmitting parameters or gradients of network. However, the non-independent and identically distributed (Non-IID) data characteristic has a negative impact on this paradigm. Furthermore, the heterogeneity of communication quality will significantly affect the accuracy of parameter transmission, causing a degradation in the performance of the FL system or even preventing its convergence. This letter proposes a dual-segment clustering (DSC) …

abstract arxiv clustering communication cs.ai cs.dc cs.lg data distributed efficiency environments federated learning however impact independent low machine machine learning negative network paradigm parameters quality segment strategy type will