3 papers
cs.LG2025
Joint Graph Estimation and Signal Restoration for Robust Federated Learning
Tsutahiro Fukuhara, Junya Hara, Hiroshi Higashi +1
We propose a robust aggregation method for model parameters in federated learning (FL) under noisy communications. FL is a distributed machine learning paradigm in which a central…
cs.CV2024
Multiscale Graph Construction Using Non-local Cluster Features
Reina Kaneko, Hayate Kojima, Kenta Yanagiya +3
This paper presents a multiscale graph construction method using both graph and signal features. Multiscale graph is a hierarchical representation of the graph, where a node at eac…
cs.LG2024
Optimizing in NN Graphs with Graph Learning Perspective
Asuka Tamaru, Junya Hara, Hiroshi Higashi +2
In this paper, we propose a method, based on graph signal processing, to optimize the choice of in -nearest neighbor graphs (NNGs). NN is one of the most popular appro…