Search papers, labs, and topics across Lattice.
This work was partially supported by the Major Program of Shandong Provincial Natural Science Foundation for the Fundamental Research under Grant ZR2022ZD03, NSF of China under Grants 62272256, 62202250, and 62372092, the Natural Science Foundation of Sichuan Province under Grant 2025ZNSFSC0512, the Colleges and Universities 20 Terms Foundation of Jinan City under Grant 202228093, and the Shandong Province Youth Innovation Team Project under Grant 2024KJH032. (Corresponding author
1
0
2
0
Overcome performance degradation in heterogeneous federated learning by contrasting current models with historical training states, leading to more stable and accurate global models.
