| 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 – 2022-03-31
|
| キーワード | large graph / Convex clustering / graph neural networks |
|---|
| 研究実績の概要 |
This year, we are still working toward the main goal of learning sound models of graphs and their applications. We have found applications of graphs and sparse structured data in different situations. One is the case of sparse data in Bayesian streaming learning.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
3: やや遅れている
理由
We are still stuck at the main goal of learning sound models of graphs. However, recent advances in learning on graphs offered some hope. While it is difficult to prove the soundness of graph models, one can prove its value in extreme cases. We are planning on this direction, to prove the soundness of these models on semi-supervised learning with very few labelled training data and learning representations of nodes on graphs.
|
| 今後の研究の推進方策 |
We are still in search of the sound models of graphs as the main goal. Other than that, we will find applications of graph in different situations such as in convex clustering.
|
| 次年度使用額が生じた理由 |
Due to covid-19 pandemic, we could not use the research budget as planned.
|
