no code implementations • 15 Jan 2024 • Shunya Kato, Masaki Saito, katsuhiko Ishiguro, Sol Cummings
However, existing methods deal solely with single-polarization images and cannot handle the multi-polarization images captured by modern satellites.
no code implementations • 2 Oct 2020 • katsuhiko Ishiguro, Kazuya Ujihara, Ryohto Sawada, Hirotaka Akita, Masaaki Kotera
Especially, the pre-training plus fine-tuning approach boosts the accuracy scores of the baseline, achieving the new state-of-the-art.
no code implementations • ICML 2020 • Ruixiang Zhang, Masanori Koyama, katsuhiko Ishiguro
Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning.
no code implementations • 12 Jun 2020 • Katsuhiko Ishiguro, Kenta Oono, Kohei Hayashi
A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules.
no code implementations • 30 Sep 2019 • Shion Honda, Hirotaka Akita, katsuhiko Ishiguro, Toshiki Nakanishi, Kenta Oono
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics.
no code implementations • 25 Sep 2019 • Kaushalya Madhawa, katsuhiko Ishiguro, Kosuke Nakago, Motoki Abe
In contrast, our model is the first invertible model for the whole graph components: both of dequantized node attributes and adjacency tensor are converted into latent vectors through two novel invertible flows.
1 code implementation • 4 Feb 2019 • Katsuhiko Ishiguro, Shin-ichi Maeda, Masanori Koyama
Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science.
no code implementations • 12 Sep 2016 • Mikio Morii, Shiro Ikeda, Nozomu Tominaga, Masaomi Tanaka, Tomoki Morokuma, katsuhiko Ishiguro, Junji Yamato, Naonori Ueda, Naotaka Suzuki, Naoki Yasuda, Naoki Yoshida
We present an application of machine-learning (ML) techniques to source selection in the optical transient survey data with Hyper Suprime-Cam (HSC) on the Subaru telescope.
Instrumentation and Methods for Astrophysics
no code implementations • 16 Sep 2014 • Katsuhiko Ishiguro, Issei Sato, Naonori Ueda
The Infinite Relational Model (IRM) is a probabilistic model for relational data clustering that partitions objects into clusters based on observed relationships.
no code implementations • NeurIPS 2010 • Katsuhiko Ishiguro, Tomoharu Iwata, Naonori Ueda, Joshua B. Tenenbaum
We propose a new probabilistic model for analyzing dynamic evolutions of relational data, such as additions, deletions and split & merge, of relation clusters like communities in social networks.