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

Matrix Factorization-based Efficient Learning for Neural Networks

Research Project

Project/Area Number 18K11457
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionGunma University (2020)
The University of Tokyo (2019)
Osaka University (2018)

Principal Investigator

Hayashi Katsuhiko  群馬大学, 社会情報学部, 准教授 (50725794)

Co-Investigator(Kenkyū-buntansha) 高瀬 翔  日本電信電話株式会社NTTコミュニケーション科学基礎研究所, 協創情報研究部, リサーチアソシエイト (40817483)
上垣外 英剛  東京工業大学, 科学技術創成研究院, 助教 (40817649)
Project Period (FY) 2018-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2020: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords行列分解 / ニューラルネットワーク / 知識グラフ / テンソル分解 / 高速フーリエ変換
Outline of Final Research Achievements

A theoretical and empirical investigation was carried out on efficient neural network computations based on matrix factorization and its generalization to multi-dimensional data, which is called tensor factorization. Especially, we developed a unitary diagonalization method to transform matrices into vectors. To show the effectiveness of the method, we conducted experiments on graph-path query answering task. In addtion, we also studied a binarization method for neural network model compression.

Academic Significance and Societal Importance of the Research Achievements

ニューラルネットワークを基礎とした表現学習や深層学習は人工知能の中核を担う技術である。その計算効率の向上は様々な人工知能アプリケーションの実用化に向けて重要な意義を持つ。ユニタリ対角化に基づく手法は行列パラメータをベクトル化する汎用的な手法であり、自然言語処理や情報検索など様々な分野におけるアプリケーションの処理効率を向上させる。また、二値化についてもシステムのメモリ消費を大幅に削減し、上記分野の様々なアプリケーションの実用化に貢献するものである。

Report

(4 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (10 results)

All 2021 2020 2019 2018 Other

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 2 results) Presentation (7 results) (of which Int'l Joint Research: 2 results,  Invited: 2 results) Remarks (1 results)

  • [Journal Article] Binarized Embeddings for Fast, Space-Efficient Knowledge Graph Completion2021

    • Author(s)
      Katsuhiko Hayashi、Koki Kishimoto、Masashi Shimbo
    • Journal Title

      IEEE Transactions on Knowledge and Data Engineering

      Volume: -- Pages: 1-13

    • DOI

      10.1109/tkde.2021.3075070

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] A Greedy Bit-flip Training Algorithm for Binarized Knowledge Graph Embeddings2020

    • Author(s)
      Hayashi Katsuhiko、Kishimoto Koki、Shimbo Masashi
    • Journal Title

      Findings of the Association for Computational Linguistics: EMNLP 2020

      Volume: - Pages: 109-114

    • DOI

      10.18653/v1/2020.findings-emnlp.10

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] Binarized Knowledge Graph Embeddings2019

    • Author(s)
      Kishimoto Koki、Hayashi Katsuhiko、Akai Genki、Shimbo Masashi、Komatani Kazunori
    • Organizer
      41st European Conference on Information Retrieval
    • Related Report
      2019 Research-status Report
  • [Presentation] A Non-commutative Bilinear Model for Answering Path Queries in Knowledge Graphs2019

    • Author(s)
      Hayashi Katsuhiko、Shimbo Masashi
    • Organizer
      the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing
    • Related Report
      2019 Research-status Report
  • [Presentation] Block HolE: 関係行列の同時対角化に基づく知識グラフ埋め込みの問題点とその解決2018

    • Author(s)
      林克彦, 真鍋陽俊, 石原敬大, 新保仁
    • Organizer
      研究報告音声言語情報処理(SLP)
    • Related Report
      2018 Research-status Report
  • [Presentation] Neural Tensor Networks with Diagonal Slice Matrices2018

    • Author(s)
      Takahiro Ishihara, Katsuhiko Hayashi, Hitoshi Manabe, Masashi Shimbo
    • Organizer
      The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] Higher-order Syntactic Attention Network for Long Sentence Compression2018

    • Author(s)
      Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Masaaki Nagata
    • Organizer
      The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] 知識グラフと分散表現2018

    • Author(s)
      林克彦
    • Organizer
      第21回情報論的学習理論ワークショップ
    • Related Report
      2018 Research-status Report
    • Invited
  • [Presentation] 知識グラフと分散表現2018

    • Author(s)
      林克彦
    • Organizer
      言語処理学会第25回年次大会
    • Related Report
      2018 Research-status Report
    • Invited
  • [Remarks] 大阪大学 RESOU

    • URL

      https://resou.osaka-u.ac.jp/en/research/2019/20190522_1

    • Related Report
      2019 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi