• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2022 年度 実施状況報告書

データコラボレーション解析による分散協調特徴量選択手法の研究

研究課題

研究課題/領域番号 22K12144
研究機関筑波大学

研究代表者

叶 秀彩  筑波大学, システム情報系, 助教 (60814001)

研究期間 (年度) 2022-04-01 – 2026-03-31
キーワードfeature selection / active feature selection
研究実績の概要

In this year, we mainly address the active feature selection-based method and application. Most existing feature selection methods focus on statically selecting the same informative features for each subtype and fail to consider the heterogeneity of samples which causes pattern differences in each subtype. We consider active feature selection to dynamically acquire different features in each subtype by combining the subtype classifier with the reinforcement learning (RL) agent in a cost-sensitive manner. We apply active feature selection for gene signature identification in renal cell carcinoma, which can select different gene signatures for different renal cell carcinoma subtypes.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

To explore different informative feature subsets for each subtype, we propose a novel active feature selection method and apply it to gene signature identification in renal cell carcinoma. By combining the subtype classifier with the reinforcement learning (RL) agent, our method can sequentially select the active features in each sample in a cost-sensitive manner. The application for gene signature identification in renal cell carcinoma show that our method can select different gene signatures for different renal cell carcinoma subtypes.

今後の研究の推進方策

Next step, we will further consider distributed datasets. We will propose distributed collaborative feature learning methods and consider privacy preserving. Intermediate representation based methods and federated learning will be applied to design the distributed feature selection framework for data collaboration. We also consider to apply our method to distributed multi-view datasets for multi-view data collaboration.

次年度使用額が生じた理由

Due to the COVID-19 pandemic, the international conference that I was planning to attend has been canceled.
I plan to join the international conference and collect the information about the latest research on feature learning and distributed data analysis.

  • 研究成果

    (8件)

すべて 2023 2022 その他

すべて 国際共同研究 (1件) 雑誌論文 (3件) (うち国際共著 1件、 査読あり 3件) 学会発表 (4件) (うち国際学会 4件、 招待講演 1件)

  • [国際共同研究] Xidian University(中国)

    • 国名
      中国
    • 外国機関名
      Xidian University
  • [雑誌論文] Interactive gene identification for cancer subtyping based on multi-omics clustering2023

    • 著者名/発表者名
      Ye Xiucai、Shi Tianyi、Cui Yaxuan、Sakurai Tetsuya
    • 雑誌名

      Methods

      巻: 211 ページ: 61~67

    • DOI

      10.1016/j.ymeth.2023.02.005

    • 査読あり
  • [雑誌論文] Sequential reinforcement active feature learning for gene signature identification in renal cell carcinoma2022

    • 著者名/発表者名
      Huang Meng、Ye Xiucai、Imakura Akira、Sakurai Tetsuya
    • 雑誌名

      Journal of Biomedical Informatics

      巻: 128 ページ: 104049~104049

    • DOI

      10.1016/j.jbi.2022.104049

    • 査読あり
  • [雑誌論文] Multiview network embedding for drug-target Interactions prediction by consistent and complementary information preserving2022

    • 著者名/発表者名
      Shang Yifan、Ye Xiucai、Futamura Yasunori、Yu Liang、Sakurai Tetsuya
    • 雑誌名

      Briefings in Bioinformatics

      巻: 23 ページ: -

    • DOI

      10.1093/bib/bbac059

    • 査読あり / 国際共著
  • [学会発表] Collaborative Future Selection for Distributed Data2023

    • 著者名/発表者名
      Ye Xiucai; Imakura Akira; Sakurai Tetsuya
    • 学会等名
      SIAM Conference on Computational Science and Engineering (CSE23)
    • 国際学会
  • [学会発表] Cost-Efficient Integrated Analysis of Distributed Data in Secure Environments2023

    • 著者名/発表者名
      Sakurai Tetsuya; Imakura Akira; Ye Xiucai; Bogdanova Anna
    • 学会等名
      SIAM Conference on Computational Science and Engineering (CSE23)
    • 国際学会
  • [学会発表] Multiview Network Embedding for Drug-target Interaction Prediction2023

    • 著者名/発表者名
      Ye Xiucai; Shang Yifan; Futamura Yasunori; Sakurai Tetsuya
    • 学会等名
      International Conference on Machine Learning and Computing (ICMLC)
    • 国際学会 / 招待講演
  • [学会発表] Ensemble Learning for Cluster Number Detection Based on Shared Nearest Neighbor Graph and Spectral Clustering2022

    • 著者名/発表者名
      Weihang Zhang, Xiucai Ye, Testuya Sakurai
    • 学会等名
      International Joint Conference on Neural Networks (IJCNN)
    • 国際学会

URL: 

公開日: 2023-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi