TY - GEN
T1 - Nested subspace arrangement for representation of relational data
AU - Hata, Nozomi
AU - Kaji, Shizuo
AU - Yoshida, Akihiro
AU - Fujisawa, Katsuki
N1 - Funding Information:
This research project was supported by the Japan Science and Technology Agency (JST), the Core Research of Evolutionary Science and Technology (CREST), the Center of Innovation Science and Technology based Radical Innovation and Entrepreneurship Program (COI Program), JSPS KAKENHI Grant No. JP 16H01707
Publisher Copyright:
© International Conference on Machine Learning, ICML 2020. All rights reserved.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85105349694&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105349694&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85105349694
T3 - 37th International Conference on Machine Learning, ICML 2020
SP - 4085
EP - 4095
BT - 37th International Conference on Machine Learning, ICML 2020
A2 - Daume, Hal
A2 - Singh, Aarti
PB - International Machine Learning Society (IMLS)
T2 - 37th International Conference on Machine Learning, ICML 2020
Y2 - 13 July 2020 through 18 July 2020
ER -