Be More with Less: Hypergraph Attention Networks for Inductive Text Classification

Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, Huan Liu


Abstract
Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are: (1) unable to capture high-order interaction between words; (2) inefficient to handle large datasets and new documents. To address those issues, in this paper, we propose a principled model – hypergraph attention networks (HyperGAT), which can obtain more expressive power with less computational consumption for text representation learning. Extensive experiments on various benchmark datasets demonstrate the efficacy of the proposed approach on the text classification task.
Anthology ID:
2020.emnlp-main.399
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4927–4936
Language:
URL:
https://aclanthology.org/2020.emnlp-main.399
DOI:
10.18653/v1/2020.emnlp-main.399
Bibkey:
Cite (ACL):
Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, and Huan Liu. 2020. Be More with Less: Hypergraph Attention Networks for Inductive Text Classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4927–4936, Online. Association for Computational Linguistics.
Cite (Informal):
Be More with Less: Hypergraph Attention Networks for Inductive Text Classification (Ding et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.399.pdf
Video:
 https://slideslive.com/38938658
Code
 kaize0409/HyperGAT