2021 Fiscal Year Research-status Report
Machine Learning on Large Graphs
| Project/Area Number |
18K11434
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Keywords | large graph / machine learning / graph neural networks |
|---|
| Outline of Annual Research Achievements |
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.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
We are making reasonable progress on specific topics of the project.
|
| Strategy for Future Research Activity |
We plan to continue working on application of graph on learning problems on different domains: biological networks, chemical compounds and knowledge graphs.
|
| Causes of Carryover |
Due to covid-19 pandemic, the research expenses could not be used for this fiscal year.
|
