Ryoma Sato
Ryoma Sato
確認したメール アドレス: ml.ist.i.kyoto-u.ac.jp - ホームページ
タイトル
引用先
引用先
Approximation ratios of graph neural networks for combinatorial problems
R Sato, M Yamada, H Kashima
arXiv preprint arXiv:1905.10261, 2019
302019
A survey on the expressive power of graph neural networks
R Sato
arXiv preprint arXiv:2003.04078, 2020
262020
Random features strengthen graph neural networks
R Sato, M Yamada, H Kashima
Proceedings of the 2021 SIAM International Conference on Data Mining (SDM …, 2021
172021
Short-term precipitation prediction with skip-connected prednet
R Sato, H Kashima, T Yamamoto
International Conference on Artificial Neural Networks, 373-382, 2018
92018
Fast unbalanced optimal transport on tree
R Sato, M Yamada, H Kashima
arXiv preprint arXiv:2006.02703, 2020
72020
Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces
R Sato, M Cuturi, M Yamada, H Kashima
arXiv preprint arXiv:2002.01615, 2020
32020
Constant time graph neural networks
R Sato, M Yamada, H Kashima
arXiv preprint arXiv:1901.07868, 2019
32019
Learning to Sample Hard Instances for Graph Algorithms
R Sato, M Yamada, H Kashima
Asian Conference on Machine Learning, 503--518, 2019
3*2019
Poincare: Recommending Publication Venues via Treatment Effect Estimation
R Sato, M Yamada, H Kashima
arXiv preprint arXiv:2010.09157, 2020
12020
Feature robust optimal transport for high-dimensional data
M Petrovich, C Liang, R Sato, Y Liu, YHH Tsai, L Zhu, Y Yang, ...
arXiv preprint arXiv:2005.12123, 2020
12020
Re-evaluating Word Mover's Distance
R Sato, M Yamada, H Kashima
arXiv preprint arXiv:2105.14403, 2021
2021
Enumerating Fair Packages for Group Recommendations
R Sato
arXiv preprint arXiv:2105.14423, 2021
2021
Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data?
R Sato
arXiv preprint arXiv:2105.12353, 2021
2021
Supervised Tree-Wasserstein Distance
Y Takezawa, R Sato, M Yamada
arXiv preprint arXiv:2101.11520, 2021
2021
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–14