English

ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification

Computation and Language 2022-04-12 v1

Abstract

Compared to sequential learning models, graph-based neural networks exhibit excellent ability in capturing global information and have been used for semi-supervised learning tasks. Most Graph Convolutional Networks are designed with the single-dimensional edge feature and failed to utilise the rich edge information about graphs. This paper introduces the ME-GCN (Multi-dimensional Edge-enhanced Graph Convolutional Networks) for semi-supervised text classification. A text graph for an entire corpus is firstly constructed to describe the undirected and multi-dimensional relationship of word-to-word, document-document, and word-to-document. The graph is initialised with corpus-trained multi-dimensional word and document node representation, and the relations are represented according to the distance of those words/documents nodes. Then, the generated graph is trained with ME-GCN, which considers the edge features as multi-stream signals, and each stream performs a separate graph convolutional operation. Our ME-GCN can integrate a rich source of graph edge information of the entire text corpus. The results have demonstrated that our proposed model has significantly outperformed the state-of-the-art methods across eight benchmark datasets.

Keywords

Cite

@article{arxiv.2204.04618,
  title  = {ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification},
  author = {Kunze Wang and Soyeon Caren Han and Siqu Long and Josiah Poon},
  journal= {arXiv preprint arXiv:2204.04618},
  year   = {2022}
}

Comments

ICLR 2022 on DLG4NLP

R2 v1 2026-06-24T10:43:31.149Z