A study on optimizing graphs for machine learning algorithms

• Project/Area Number: 24800036
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Intelligent informatics
• Research Institution: Kyoto University
• Principal Investigator: KARASUYAMA Masayuki 京都大学, 化学研究所, 助教 (40628640)
• Project Period (FY): 2012-08-31 – 2014-03-31
• Project Status: Completed (Fiscal Year 2013)
• Budget Amount: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000); Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
• Keywords: 機械学習 / グラフ / バイオインフォマティクス / 半教師付き学習

Research Abstract

A variety types of network data have been attracted wide attention, such as protein interaction network in biology and link relationships in social networks. This research has studied statistical algorithms to analyze these network data, which can be represented as ``graph'', and developed highly accurate methods for prediction problem on graphs compared to existing approaches.

Research Products

• [Journal Article] Multiple Graph Label Propagation by Sparse Integration (2013)
  • Author(s): Karasuyama, M. and Mamitsuka, H.
  • Journal Title: IEEE Transactions on Neural Networks and Learning Systems Volume: 24 Issue: 12 Pages: 1999-2012
  • DOI: 10.1109/tnnls.2013.2271327
  • Peer Reviewed
• [Presentation] Manifold-based Similarity Adaptation for Label Propagation (2013)
  • Author(s): M Karasuyama, and H Mamitsuka
  • Organizer: Advances in Neural Information Processing Systems (NIPS)
• [Presentation] 局所線形近似に基づくラベル伝播のための類似度適合 (2013)
  • Author(s): 烏山昌幸, 馬見塚拓
  • Organizer: 情報論的学習理論と機械学習研究会 (IBISML)
• [Presentation] Manifold-based Similarity Adaptation for Label Propagation (2013)
  • Author(s): M. Karasuyama and H. Mamitsuka
  • Organizer: Neural Information Processing Systems
  • Place of Presentation: Lake Taho, Nevada, US
• [Presentation] 局所線形近似に基づくラベル伝播のための類似度適合 (2013)
  • Author(s): 烏山昌幸
  • Organizer: 情報論的学習理論と機械学習研究会
  • Place of Presentation: 名古屋工業大学
• [Presentation] ラベル伝播アルゴリズムにおける複数グラフのスパース結合法 (2012)
  • Author(s): 烏山昌幸, 馬見塚拓
  • Organizer: 情報論的学習理論と機械学習研究会 (IBISML)
• [Presentation] ラベル伝播アルゴリズムにおける複数グラフのスパース結合法 (2012)
  • Author(s): 烏山昌幸
  • Organizer: 第15回情報論的学習理論ワークショップ
  • Place of Presentation: 筑波大学 東京キャンパス文京校舎