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

2020/11/01 by Kaize Ding, Ding, Kaize, Jianling Wang +7 · 6 citations
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2011.00387

Accepted by EMNLP 2020

arxiv created 2020/11/01 · openalex publication_date 2020/11/01 · arxiv updated 2020/11/03 · openalex created_date 2020/11/09 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• Neural Message Passing for Quantum Chemistry
• Inductive Representation Learning on Large Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Convolutional Neural Networks for Sentence Classification
• Hypergraph convolution and hypergraph attention

Cited by

• A Novel Graph-Sequence Learning Model for Inductive Text Classification
• Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification
• Disentangling Hyperedges through the Lens of Category Theory
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods
• Multi-Granular Attention based Heterogeneous Hypergraph Neural Network

Related

• Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
• InducT-GCN: Inductive Graph Convolutional Networks for Text Classification
• A text classification method based on LSTM and graph attention network
• Text Level Graph Neural Network for Text Classification