TY - GEN
T1 - Computationally efficient wasserstein loss for structured labels
AU - Toyokuni, Ayato
AU - Yokoi, Sho
AU - Kashima, Hisashi
AU - Yamada, Makoto
N1 - Funding Information:
This work was supported by the JSPS KAKENHI Grant Number 20H04243 and 20H04244. This work was also supported by JST, ACT-X Grant Number JPMJAX200S, Japan.
Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation. We propose a tree-Wasserstein distance regularized LDL algorithm, focusing on hierarchical text classification tasks. We propose predicting the entire label hierarchy using neural networks, where the similarity between predicted and true labels is measured using the tree-Wasserstein distance. Through experiments using synthetic and real-world datasets, we demonstrate that the proposed method successfully considers the structure of labels during training, and it compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.
AB - The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation. We propose a tree-Wasserstein distance regularized LDL algorithm, focusing on hierarchical text classification tasks. We propose predicting the entire label hierarchy using neural networks, where the similarity between predicted and true labels is measured using the tree-Wasserstein distance. Through experiments using synthetic and real-world datasets, we demonstrate that the proposed method successfully considers the structure of labels during training, and it compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.
UR - http://www.scopus.com/inward/record.url?scp=85107432655&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107432655&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85107432655
T3 - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
SP - 1
EP - 7
BT - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
PB - Association for Computational Linguistics (ACL)
T2 - 16th Conference of the European Chapter of the Associationfor Computational Linguistics: Student Research Workshop, EACL 2021
Y2 - 19 April 2021 through 23 April 2021
ER -