activity
20162021
most citedFederated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations

10 citations · 22 across the 8 of their papers we have counts for

collaborators

12 papers

math.NA20212 cited

Complex moment-based method with nonlinear transformation for computing large and sparse interior singular triplets

Akira Imakura, Tetsuya Sakurai

This paper considers computing interior singular triplets corresponding to the singular values in some interval. Based on the concept of the complex moment-based parallel eigensolv…

cs.LG20214 cited

Accuracy and Privacy Evaluations of Collaborative Data Analysis

Akira Imakura, Anna Bogdanova, Takaya Yamazoe +2

Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing…

cs.LG202010 cited

Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations

Anna Bogdanova, Akie Nakai, Yukihiko Okada +2

Dimensionality Reduction is a commonly used element in a machine learning pipeline that helps to extract important features from high-dimensional data. In this work, we explore an…

cs.LG20201 cited

Interpretable collaborative data analysis on distributed data

Akira Imakura, Hiroaki Inaba, Yukihiko Okada +1

This paper proposes an interpretable non-model sharing collaborative data analysis method as one of the federated learning systems, which is an emerging technology to analyze distr…

math.NA2020

Flexible subspace iteration with moments for an effective contour integration-based eigensolver

Sarah Huber, Yasunori Futamura, Martin Galgon +3

Contour integration schemes are a valuable tool for the solution of difficult interior eigenvalue problems. However, the solution of many large linear systems with multiple right h…

cond-mat.str-el2019

A Parallel Computing Method for the Coupled-Cluster Singles and Doubles

Takumi Yamashita, Taichi Kosugi, Yu-ichiro Matsushita +1

In this paper, we present a parallel computing method for the coupled-cluster singles and doubles (CCSD) in periodic systems. The CCSD in periodic systems solves simultaneous equat…