Hyperbolic Capsule Networks for Multi-Label Classification

Boli Chen, Xin Huang, Lin Xiao, Liping Jing


Abstract
Although deep neural networks are effective at extracting high-level features, classification methods usually encode an input into a vector representation via simple feature aggregation operations (e.g. pooling). Such operations limit the performance. For instance, a multi-label document may contain several concepts. In this case, one vector can not sufficiently capture its salient and discriminative content. Thus, we propose Hyperbolic Capsule Networks (HyperCaps) for Multi-Label Classification (MLC), which have two merits. First, hyperbolic capsules are designed to capture fine-grained document information for each label, which has the ability to characterize complicated structures among labels and documents. Second, Hyperbolic Dynamic Routing (HDR) is introduced to aggregate hyperbolic capsules in a label-aware manner, so that the label-level discriminative information can be preserved along the depth of neural networks. To efficiently handle large-scale MLC datasets, we additionally present a new routing method to adaptively adjust the capsule number during routing. Extensive experiments are conducted on four benchmark datasets. Compared with the state-of-the-art methods, HyperCaps significantly improves the performance of MLC especially on tail labels.
Anthology ID:
2020.acl-main.283
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3115–3124
Language:
URL:
https://aclanthology.org/2020.acl-main.283
DOI:
10.18653/v1/2020.acl-main.283
Bibkey:
Cite (ACL):
Boli Chen, Xin Huang, Lin Xiao, and Liping Jing. 2020. Hyperbolic Capsule Networks for Multi-Label Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3115–3124, Online. Association for Computational Linguistics.
Cite (Informal):
Hyperbolic Capsule Networks for Multi-Label Classification (Chen et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.283.pdf
Video:
 http://slideslive.com/38928778