Hiroshi Kajino

Overview

Title

Researcher

Location

IBM Research - Tokyo Tokyo, Japan

Bio

Hiroshi Kajino is a researcher at IBM Research - Tokyo. He is mainly working on machine learning and data mining areas. For more details including his publications, please refer to the external website.

Publications

MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network
- - Akihiro Kishimoto
  - Hiroshi Kajino
  - et al.
- 2023
- NeurIPS 2023
Autoencoder based on Graph and Recurrent Neural Networks and Application to Property Prediction
- - Akihiro Kishimoto
  - Hiroshi Kajino
  - et al.
- 2023
- MRS Fall Meeting 2023
A Differentiable Point Process with Its Application to Spiking Neural Networks
- - Hiroshi Kajino
- 2021
- ICML 2021
Molecular Hypergraph Grammar with Its Application to Molecular Optimization
- - Hiroshi Kajino
- 2019
- ICML 2019

Visit Google Scholar

Patents

- 08 May 2023
- US
- 11645476
Generating Symbolic Domain Models From Multimodal Data
- 15 Aug 2022
- US
- 11417415
Molecular Representation
- 14 Aug 2022
- JP
- 7123938
Learning Apparatus And Method For Bidirectional Learning Of Predictive Model Based On Data Sequence
- 08 Aug 2022
- US
- 11410077
Implementing A Computer System Task Involving Nonstationary Streaming Time-series Data By Removing Biased Gradients From Memory
- 18 Apr 2022
- US
- 11308414
Multi-step Ahead Forecasting Using Complex-valued Vector Autoregregression
- 27 Sep 2021
- US
- 11132621
Correction Of Reaction Rules Databases By Active Learning
- 21 Sep 2020
- US
- 10783452
Learning Apparatus And Method For Learning A Model Corresponding To A Function Changing In Time Series

Projects

AI in Tokyo

View more projects

Top collaborators

Akihiro Kishimoto

Senior Research Scientist

Daiju Nakano

Senior research manager, Science&Technology

Hajime Shinohara

Research Scientist

Indra Priyadarsini S

Research Scientist