| 研究課題/領域番号 |
18K11434
|
|---|
| 研究機関 | 京都大学 |
|---|
研究代表者 |
|
|---|
| 研究期間 (年度) |
2018-04-01 – 2023-03-31
|
| キーワード | large graph / machine learning / graph neural networks |
|---|
| 研究実績の概要 |
We continue to obtain results on applications of learning on graphs on different settings. One result is on graph-based feature extraction. After that, substructure weights are learnt in WWL-based kernel setting. This overcomes the problem of usual kernel construction method that component (such as substructures) weights cannot be learnt in kernels.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
We are making reasonable progress on specific topics of the project.
|
| 今後の研究の推進方策 |
We plan to continue working on application of graph on learning problems on different domains: biological networks, chemical compounds and knowledge graphs.
|
| 次年度使用額が生じた理由 |
Due to covid-19 pandemic, the research expenses could not be used for this fiscal year.
|
