| Project/Area Number |
21K12042
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
Liu Xin 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (20803935)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2023: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2022: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2021: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | graph neural network / graph embedding / graph analysis / social network / complex network / Graph Neural Network / Graph Embedding / Graph Machine Learning / Dynamic Graph / Node Classification / Imbalanced Graph / Multi-Label Graph / Geometric Learning / Graph Mining / Link Prediction |
|---|
| Outline of Research at the Start |
Graph learning has been advancing rapidly. However, several intrinsic defects hinder this technology from achieving immense success. We aim to remedy these defects and promote model evolutions. The outcome will improve the practicability of this technology and facilitate its extensive usage.
|
| Outline of Final Research Achievements |
This project has resulted in many advances in graph learning techniques. We have designed new learning architectures that achieved remarkable performance improvement. We have developed new models for heterogeneous graphs. We have proposed new practical strategies for working in various imperfect environments. We have successfully applied our approaches to many real-world applications.
|
| Academic Significance and Societal Importance of the Research Achievements |
Several intrinsic defects in the current graph learning technology have hindered its widespread success. This project addresses these defects and promotes advancements in graph learning models. Many of the ideas created in this project have already diffused in the academic and industry community.
|
