Federated learning has emerged as a promising paradigm for privacy-preserving collaborative learning across distributed clients. However, the data owned by different clients are usually highly heterogeneous and severely Non-Independent and Identically Distributed (Non-IID), which leads to client drift and unsatisfactor...
Yuxuan Luan, Zi-Lin Zhao, Wei Wang et al.· Proceedings of the 34th ACM...· 0 citations
A novel data-centric federated learning framework called FedGAT is proposed, to address severe data heterogeneity under limited communication budgets and improve the quality and diversity of condensed knowledge by preserving local geometric structure and prioritizing insufficiently learned yet non-redundant samples.
Yuxuan Luan, Zi-Lin Zhao, Wei Wang et al.· Proceedings of the 34th ACM...· 0 citations
SERM integrates topology-aware graph propagation with masked self-supervised reconstruction, a masked self-supervised framework for network-level structural representation learning that captures useful structural information and remains applicable across several network-level evaluation settings.
Jing-Jing Chen, Hai-Peng Peng, Lu Li et al.· Mathematics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.