SEAFL: Enhancing Efficiency in Semi-Asynchronous Federated Learning through Adaptive Aggregation and Selective Training

Ähnliche Einträge

• FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering
  von: Islam, Md Sirajul, et al.
  Veröffentlicht: (2024)
• FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering
  von: Islam, Md Sirajul, et al.
  Veröffentlicht: (2024)
• FedFair^3: Unlocking Threefold Fairness in Federated Learning
  von: Javaherian, Simin, et al.
  Veröffentlicht: (2024)
• FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
  von: Islam, Md Sirajul, et al.
  Veröffentlicht: (2026)
• An Experimental Study of Different Aggregation Schemes in Semi-Asynchronous Federated Learning
  von: Li, Yunbo, et al.
  Veröffentlicht: (2024)