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

Accelerating Inductive Logic Programming Using GPU

Research Project

Project/Area Number 19K11909
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60050:Software-related
Research InstitutionTokyo University of Science

Principal Investigator

Takimoto Munehiro  東京理科大学, 理工学部情報科学科, 教授 (00318205)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywords帰納論理プログラミング / Progol / GPU / RDBMS / SQL / 群知能 / 粒子群最適化 / PSO / 人工知能 / A*アルゴリズム / コンパイラ / コード最適化 / カーネルフュージョン / ILP / Datalog / 並列化 / 被覆 / 正例 / 負例
Outline of Research at the Start

本研究は,ILPが仮説を探索する際に生成する多くの仮説候補が,訓練データを満たすかどうか検証されることに着目し,まず,この検証過程をGPU によって高速化する.この検証の過程は,訓練データに含まれる正例が背景知識と仮説候補によって導出でき,負例が導出できないことを確認する点で,論理型言語の実行過程と同じであるので,論理型言語の実行をGPU 上で実現することによって,仮説の検証過程を高速化する.

Outline of Final Research Achievements

Inductive Logic Programming (ILP), which is one of explainable A.I.s., generates a hypothesis based on training data consisting of positive examples and negative examples. In the process generating the hypothesis, ILP search for the most suitable hypothesis while repeating generating hypothesis candidates and checking whether they deduct the positive examples and do not deduct the negative examples. In this project, we implement parallel checking of the examples on RDBMS with GPU execution through converting the checking into SQL operations. Furthermore, we have enabled the SQL operations to simultaneously check several hypothesis candidates, so that we have achieved making it six times faster through decreasing the overhead of RDBMS. Also, we have implemented the method that generates the hypothesis based on PSO that is one of swarm intelligence algorithms, so that we have achieved twice more speedup.

Academic Significance and Societal Importance of the Research Achievements

現在広く利用されているAIの深層学習は,学習内容がわからないために,分析ツールとして利用することは困難である.これに対して,ILPは,その学習内容を完璧に説明でき,新しいサンプルに対する推論も,推論過程を確認することができる.本研究は,説明可能AIであるILPを,並列化とメタヒューリスティクス化によって高速化し,ビックデータに適用できるようにした.今後,本AIシステムを,がんの臨床データと遺伝子データに適用することによって,予後や再発予想を行えるモデルを作成する予定である.

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (11 results)

All 2023 2022 2020 2019

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 5 results) Presentation (5 results) (of which Int'l Joint Research: 4 results) Book (1 results)

  • [Journal Article] Efficient Inductive Logic Programming based on Predictive A*-like Algorithm2023

    • Author(s)
      Meko Okawara, Junji Fukuhara, Munehiro Takimoto, Tsutomu Kumazawa and Yasushi Kambayashi
    • Journal Title

      AHFE International

      Volume: 70 Pages: 99-107

    • DOI

      10.54941/ahfe1002934

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Automated kernel fusion for GPU based on code motion2022

    • Author(s)
      Junji Fukuhara and Munehiro Takimoto
    • Journal Title

      LCTES '22: 23rd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems

      Volume: 23 Pages: 151-161

    • DOI

      10.1145/3519941.3535078

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Efficient Inductive Logic Programming Based on Particle Swarm Optimization2022

    • Author(s)
      Kyosuke Obara, Munehiro Takimoto, Tsutomu Kumazawa and Yasushi Kambayashi
    • Journal Title

      Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

      Volume: 477 Pages: 151-158

    • DOI

      10.1007/978-3-031-29126-5_13

    • ISBN
      9783031291258, 9783031291265
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Scalar Replacement Considering Branch Divergence2022

    • Author(s)
      Junji Fukuhara and Munehiro Takimoto
    • Journal Title

      Journal of Information Processing

      Volume: 30 Issue: 0 Pages: 164-178

    • DOI

      10.2197/ipsjjip.30.164

    • NAID

      130008159962

    • ISSN
      1882-6652
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Branch Divergence Reduction Based on Code Motion2020

    • Author(s)
      Junji Fukuhara and Munehiro Takimoto
    • Journal Title

      Journal of Information Processing

      Volume: 28 Issue: 0 Pages: 302-309

    • DOI

      10.2197/ipsjjip.28.302

    • NAID

      130007843339

    • ISSN
      1882-6652
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Efficient Inductive Logic Programming Based on Particle Swarm Optimization2022

    • Author(s)
      Kyosuke Obara, Munehiro Takimoto, Tsutomu Kumazawa and Yasushi Kambayashi
    • Organizer
      EAI AICON 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Meko Okawara, Junji Fukuhara, Munehiro Takimoto, Tsutomu Kumazawa and Yasushi Kambayashi2022

    • Author(s)
      Meko Okawara, Junji Fukuhara, Munehiro Takimoto, Tsutomu Kumazawa and Yasushi Kambayashi
    • Organizer
      IHIET-AI 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Capture of Multi Intruders by Cooperative Multiple Robots using Mobile Agents2020

    • Author(s)
      Tadashi Shoji, Munehiro Takimoto and Yasushi Kambayashi
    • Organizer
      International Conference on Agents and Artificial Intelligence
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] コード移動に基づく分岐発散の低減2019

    • Author(s)
      福原 淳司,滝本 宗宏
    • Organizer
      情報処理学会第126回プログラミング研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] Virtual Space Pointing Based on Vergence2019

    • Author(s)
      Yuki Hirata, Hiroki Soma, Munehiro Takimoto and Yasushi Kambayashi
    • Organizer
      International Conference on Human-Computer Interaction
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Book] Artificial Intelligence for Communications and Networks -4th EAI International Conference, AICON 2022, Hiroshima, Japan, November 30 - December 1, 2022, Proceedings2023

    • Author(s)
      Yasushi Kambayashi, Ngoc Thanh Nguyen, Shu-Heng Chen, Petre Dini, Munehiro Takimoto
    • Total Pages
      159
    • Publisher
      Springer
    • ISBN
      9783031291258
    • Related Report
      2022 Annual Research Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi