Proceedings of the Annual Conference of JSAI
Online ISSN : 2758-7347
36th (2022)
Session ID : 4Yin2-46
Conference information

Gradient-Based Communication Network Optimization for Fully Decentralized Learning
*Naoyuki TERASHITASatoshi HARA
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract

We propose a gradient-based communication network optimization algorithm for fully decentralized learning. Our algorithm traces the gradients of network edge weights throughout the training in a fully decentralized manner. We applied the proposed algorithm to convergence acceleration and evaluated its performance by simulation experiments.

Content from these authors
© 2022 The Japanese Society for Artificial Intelligence
Previous article Next article
feedback
Top