Nested subspace arrangement for representation of relational data

Nozomi Hata, Shizuo Kaji, Akihiro Yoshida, Katsuki Fujisawa

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

Studies on acquiring appropriate continuous representations of discrete objects, such as graphs and knowledge base data, have been conducted by many researchers in the field of machine learning. In this study, we introduce Nested SubSpace (NSS) arrangement, a comprehensive framework for representation learning. We show that existing embedding techniques can be regarded as special cases of the NSS arrangement. Based on the concept of the NSS arrangement, we implement a Disk-ANChor ARrangement (DANCAR), a representation learning method specialized to reproducing general graphs. Numerical experiments have shown that DANCAR has successfully embedded WordNet in R 20 with an F1 score of 0.993 in the reconstruction task. DANCAR is also suitable for visualization in understanding the characteristics of graphs.

本文言語英語
ホスト出版物のタイトル37th International Conference on Machine Learning, ICML 2020
編集者Hal Daume, Aarti Singh
出版社International Machine Learning Society (IMLS)
ページ4085-4095
ページ数11
ISBN(電子版)9781713821120
出版ステータス出版済み - 2020
イベント37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
継続期間: 7 13 20207 18 2020

出版物シリーズ

名前37th International Conference on Machine Learning, ICML 2020
PartF168147-6

会議

会議37th International Conference on Machine Learning, ICML 2020
CityVirtual, Online
Period7/13/207/18/20

All Science Journal Classification (ASJC) codes

  • 計算理論と計算数学
  • 人間とコンピュータの相互作用
  • ソフトウェア

フィンガープリント

「Nested subspace arrangement for representation of relational data」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル