Mr. Thonglek's research presentation at ICFEC 2022

Mr. Kundjanasith Thonglek (Tem), a second-year doctoral student at SDLab presented the follwing paper at the 6th IEEE International Conference on Fog and Edge Computing (ICFEC 2022)

Kundjanasith Thonglek, Keichi Takahashi, Kohei Ichikawa, Chawanat Nakasan, Pattara Leelaprute, Hajimu Iida, “Sparse Communication for Federated Learning”, 6th IEEE International Conference on Fog and Edge Computing (ICFEC 2022), May. 2022.

In this paper, we proposed a novel method to reduce the required communication cost for federated learning by transferring only top updated parameters in neural network models. The proposed method allows adjusting the criteria of updated parameters to trade-off the reduction of communication costs and the loss of model accuracy.