• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Towards Deeper Graph Neural Networks

Research Project

Project/Area Number 19K22864
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionTokyo University of Agriculture and Technology

Principal Investigator

Tanaka Yuichi  東京農工大学, 工学(系)研究科(研究院), 准教授 (10547029)

Project Period (FY) 2019-06-28 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
Fiscal Year 2020: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2019: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Keywords深層学習 / 信号処理 / グラフ信号処理 / グラフ深層学習 / 深層展開 / サンプリング / グラフニューラルネットワーク / ニューラルネットワーク
Outline of Research at the Start

グラフ深層学習は,画像等の整列したデータではなく,神経網・交通網などのネットワーク上のデータ,あるいは点群データなどの不均一に分布するデータに対する特徴抽出・分類・認識などに用いられている,深層学習の新しいパラダイムである.本研究では,真に深層とできるグラフ深層学習の実現のため,全スペクトル領域グラフ畳み込みニューラルネットワークを提案することを目標とする.

Outline of Final Research Achievements

Sampling of signals on graphs: We extend generalized sampling into graph-structured data. We reveal that various signal models studied in standard signal processing are applicable for graph signals.
Deep algorithm unrolling for graph-structured data: We propose a new deep algorithm unrolling method for graph signals. The proposed method outperforms existing graph convolutional neural networks and convex optimization algorithms in several signal restoration problems.

Academic Significance and Societal Importance of the Research Achievements

本研究では,グラフ深層学習を真に深層にするための研究に取り組んだ.成果の意義として,以下の2点が挙げられる.1)グラフ上データのシフト不変性に関する議論が必須であること.2) 深層展開と呼ばれる手法の一群がグラフ上データの解析に有効であること.
グラフ深層学習を深層とするための取り組みは機械学習分野において意義のある問いであり,これは理論なしには実現し得ない.本研究による研究成果はグラフ深層学習を真に深層とするための問題点を一部明らかにした.本点は大きな学術的意義があると思われる.

Report

(3 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • Research Products

    (6 results)

All 2021 2020 Other

All Int'l Joint Research (1 results) Journal Article (4 results) (of which Int'l Joint Research: 4 results,  Peer Reviewed: 4 results,  Open Access: 2 results) Presentation (1 results)

  • [Int'l Joint Research] ワイツマン科学研究所(イスラエル)

    • Related Report
      2019 Research-status Report
  • [Journal Article] Graph signal denoising using nested-structured deep algorithm unrolling2021

    • Author(s)
      M. Nagahama, K. Yamada, Y. Tanaka, S. H. Chan, and Y. C. Eldar
    • Journal Title

      Proceedings of 2021 IEEE ICASSP

      Volume: 1 Pages: 1-5

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Sampling Signals on Graphs: From Theory to Applications2020

    • Author(s)
      Tanaka Yuichi、Eldar Yonina C.、Ortega Antonio、Cheung Gene
    • Journal Title

      IEEE Signal Processing Magazine

      Volume: 37 Issue: 6 Pages: 14-30

    • DOI

      10.1109/msp.2020.3016908

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Generalized Sampling on Graphs With Subspace and Smoothness Priors2020

    • Author(s)
      Tanaka Yuichi、Eldar Yonina C.
    • Journal Title

      IEEE Transactions on Signal Processing

      Volume: 68 Pages: 2272-2286

    • DOI

      10.1109/tsp.2020.2982325

    • Related Report
      2020 Annual Research Report 2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Generalized Graph Spectral Sampling with Stochastic Priors2020

    • Author(s)
      Hara Junya、Tanaka Yuichi、Eldar Yonina C.
    • Journal Title

      Proceedings of 2020 IEEE ICASSP

      Volume: 1 Pages: 1-5

    • DOI

      10.1109/icassp40776.2020.9053720

    • Related Report
      2020 Annual Research Report 2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] 入れ子型深層展開を用いたグラフ信号復元2021

    • Author(s)
      長濱直智,山田宏樹,田中雄一
    • Organizer
      2021年電子情報通信学会総合大会
    • Related Report
      2020 Annual Research Report

URL: 

Published: 2019-07-04   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi