17 citations · 19 across the 18 of their papers we have counts for
5 papers · 1 filter
FedLoRD: Personalized Federated Learning based on Low-Rank Structures of Model Parameter Differences
Tsutahiro Fukuhara, Junya Hara, Hiroshi Higashi +1
We propose FedLoRD, a personalized federated learning (PFL) method based on the low-rank structure of the differences between the global and personalized model parameters. PFL is a…
Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming
Haruki Yokota, Hiroshi Higashi, Yuichi Tanaka +1
Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph is a signed gr…
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…
Efficient Learning of Balanced Signed Graphs via Iterative Linear Programming
Haruki Yokota, Hiroshi Higashi, Yuichi Tanaka +1
Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph has no cycles…
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…