Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

arXiv:2403.14371v1 Announce Type: new
Abstract: In federated learning, data heterogeneity significantly impacts performance. A typical solution involves segregating these parameters into shared and personalized components, a concept also relevant in multi-task learning. Addressing this, we propose "Loop Improvement" (LI), a novel method enhancing this separation and feature extraction without necessitating a central server or data interchange among participants. Our experiments reveal LI's superiority in several aspects: In personalized federated learning environments, LI consistently outperforms the advanced FedALA algorithm in accuracy …

arxiv cs.ai cs.dc cs.lg data features improvement loop server type