Nested Subspace Arrangement for Representation of Relational Data

Nozomi Hata, Shizuo Kaji, Akihiro Yoshida, Katsuki Fujisawa
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:4127-4137, 2020.

Abstract

Studies of acquiring appropriate continuous representations of a discrete objects such as graph and knowledge based data have been conducted by many researches in the field of machine learning. In this paper, we introduce Nested SubSpace arrangement (NSS arrangement), a comprehensive framework for representation learning. We show that existing embedding techniques can be regarded as a member of NSS arrangement. Based on the concept of the NSS arrangement, we implemented Disk-ANChor ARrangement (DANCAR), a representation learning method specializing to reproduce general graphs. Numerical experiments have shown that DANCAR has successfully embedded WordNet in ${\mathbb R}^{20}$ with the F1 score of 0.993 in the reconstruction task. DANCAR is also suitable for visualization to understand the characteristics of graph.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-hata20a, title = {Nested Subspace Arrangement for Representation of Relational Data}, author = {Hata, Nozomi and Kaji, Shizuo and Yoshida, Akihiro and Fujisawa, Katsuki}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {4127--4137}, year = {2020}, editor = {Hal Daumé III and Aarti Singh}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/hata20a/hata20a.pdf}, url = { http://proceedings.mlr.press/v119/hata20a.html }, abstract = {Studies of acquiring appropriate continuous representations of a discrete objects such as graph and knowledge based data have been conducted by many researches in the field of machine learning. In this paper, we introduce Nested SubSpace arrangement (NSS arrangement), a comprehensive framework for representation learning. We show that existing embedding techniques can be regarded as a member of NSS arrangement. Based on the concept of the NSS arrangement, we implemented Disk-ANChor ARrangement (DANCAR), a representation learning method specializing to reproduce general graphs. Numerical experiments have shown that DANCAR has successfully embedded WordNet in ${\mathbb R}^{20}$ with the F1 score of 0.993 in the reconstruction task. DANCAR is also suitable for visualization to understand the characteristics of graph.} }
Endnote
%0 Conference Paper %T Nested Subspace Arrangement for Representation of Relational Data %A Nozomi Hata %A Shizuo Kaji %A Akihiro Yoshida %A Katsuki Fujisawa %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-hata20a %I PMLR %P 4127--4137 %U http://proceedings.mlr.press/v119/hata20a.html %V 119 %X Studies of acquiring appropriate continuous representations of a discrete objects such as graph and knowledge based data have been conducted by many researches in the field of machine learning. In this paper, we introduce Nested SubSpace arrangement (NSS arrangement), a comprehensive framework for representation learning. We show that existing embedding techniques can be regarded as a member of NSS arrangement. Based on the concept of the NSS arrangement, we implemented Disk-ANChor ARrangement (DANCAR), a representation learning method specializing to reproduce general graphs. Numerical experiments have shown that DANCAR has successfully embedded WordNet in ${\mathbb R}^{20}$ with the F1 score of 0.993 in the reconstruction task. DANCAR is also suitable for visualization to understand the characteristics of graph.
APA
Hata, N., Kaji, S., Yoshida, A. & Fujisawa, K.. (2020). Nested Subspace Arrangement for Representation of Relational Data. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:4127-4137 Available from http://proceedings.mlr.press/v119/hata20a.html .

Related Material