activity
20192022
collaborators

7 papers

cs.LG2021

Supervised Tree-Wasserstein Distance

Yuki Takezawa, Ryoma Sato, Makoto Yamada

To measure the similarity of documents, the Wasserstein distance is a powerful tool, but it requires a high computational cost. Recently, for fast computation of the Wasserstein di…

cs.LG2020

Fast Unbalanced Optimal Transport on a Tree

Ryoma Sato, Makoto Yamada, Hisashi Kashima

This study examines the time complexities of the unbalanced optimal transport problems from an algorithmic perspective for the first time. We reveal which problems in unbalanced op…

cs.LG2020

A Survey on The Expressive Power of Graph Neural Networks

Ryoma Sato

Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have…

cs.LG2020

Random Features Strengthen Graph Neural Networks

Ryoma Sato, Makoto Yamada, Hisashi Kashima

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have bee…

stat.ML2020

Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces

Ryoma Sato, Marco Cuturi, Makoto Yamada +1

Comparing two probability measures supported on heterogeneous spaces is an increasingly important problem in machine learning. Such problems arise when comparing for instance two p…

cs.LG2019

Approximation Ratios of Graph Neural Networks for Combinatorial Problems

Ryoma Sato, Makoto Yamada, Hisashi Kashima

In this paper, from a theoretical perspective, we study how powerful graph neural networks (GNNs) can be for learning approximation algorithms for combinatorial problems. To this e…