Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification

Soumya Chatterjee, Ayush Maheshwari, Ganesh Ramakrishnan, Saketha Nath Jagarlapudi


Abstract
We consider the problem of multi-label classification, where the labels lie on a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the recent success of hyperbolic embeddings in capturing hierarchical relations, we propose to jointly learn the classifier parameters as well as the label embeddings. Such a joint learning is expected to provide a twofold advantage: i) the classifier generalises better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy. We propose a novel formulation for the joint learning and empirically evaluate its efficacy. The results show that the joint learning improves over the baseline that employs label co-occurrence based pre-trained hyperbolic embeddings. Moreover, the proposed classifiers achieve state-of-the-art generalization on standard benchmarks. We also present evaluation of the hyperbolic embeddings obtained by joint learning and show that they represent the hierarchy more accurately than the other alternatives.
Anthology ID:
2021.eacl-main.247
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2829–2841
Language:
URL:
https://aclanthology.org/2021.eacl-main.247
DOI:
10.18653/v1/2021.eacl-main.247
Bibkey:
Cite (ACL):
Soumya Chatterjee, Ayush Maheshwari, Ganesh Ramakrishnan, and Saketha Nath Jagarlapudi. 2021. Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2829–2841, Online. Association for Computational Linguistics.
Cite (Informal):
Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification (Chatterjee et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.247.pdf
Code
 soumyac1999/hyperbolic-label-emb-for-hmc
Data
New York Times Annotated CorpusRCV1