Machine Learning for Structure-Rich Data-Scarce Domains
| Project/Area Number |
22K12150
|
|---|
| 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 | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2022-04-01 – 2025-03-31
|
| Project Status |
Granted (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2024: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | Graph neural networks / machine learning / Machine learning / Structured data / Deep learning / Sparse learning |
|---|
| Outline of Research at the Start |
There are three directions of this research project:
(1) investigating original machine learning models for complicated structures,
(2) designing novel structure discovery tools incorporating domain knowledge, and
(3) discovering new biomedical knowledge to be used by domain experts.
|
| Outline of Annual Research Achievements |
We are working on the topic of predicting properties of two drugs, formulated as a pair of graphs. Due to its potential high dimensionality and small scale data, we have to leverage more data from different sources to avoid overfitting. The solution is to learn representation of two drugs within a network of drugs, proteins and other biological information.
|
| 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 have found some small but novel methods for particular problem of learning representations of two drugs in its special context.
|
| Strategy for Future Research Activity |
We continue to investigate learning problem with small data by leveraging information from other source to learn reliably.
|
Report
(1 results)
Research Products
(2 results)
