Studies on link analytic similarity measures for high-dimensional/structured data
Project/Area Number |
24300057
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Nara Institute of Science and Technology |
Principal Investigator |
Shimbo Masashi 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (90311589)
|
Co-Investigator(Kenkyū-buntansha) |
HARA Kazuo 国立遺伝学研究所, 生命情報研究センター, 研究員 (30467691)
SUZUKI Ikumi 山形大学, 理工学研究科, 助教 (20637730)
|
Project Period (FY) |
2012-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥17,680,000 (Direct Cost: ¥13,600,000、Indirect Cost: ¥4,080,000)
Fiscal Year 2014: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2013: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2012: ¥7,020,000 (Direct Cost: ¥5,400,000、Indirect Cost: ¥1,620,000)
|
Keywords | リンク解析 / 高次元データ / 近傍検索 / ハブ / 類似度尺度 / 距離尺度 / データマイニング / 類似度 / テキストマイニング |
Outline of Final Research Achievements |
Building on the latest findings in link analysis and machine learning, this research project developed and characterized various similarity measures for high-dimensional or structured data. In particular, our main focus was to investigate the influence of hubs, which can be observed both in vector space and on graph data. We proposed several techniques to reduce the emergence of hubs. The effectiveness of these techniques was evaluated on natural language processing tasks, in which the data is known to be extremely high-dimensional.
|
Report
(5 results)
Research Products
(22 results)