Word Grounded Graph Convolutional Network

TL;DR

This paper introduces a word-grounded graph convolutional network (WGCN) that leverages a word-level graph to improve text classification, especially for out-of-graph documents, by decoupling data samples from the model.

Contribution

The paper proposes transforming document graphs into word graphs to enable inductive learning and handle out-of-graph documents effectively.

Findings

WGCN outperforms existing methods in text classification tasks.

The model effectively incorporates global semantic dependencies.

WGCN demonstrates improved efficiency in learning representations.

Abstract

Graph Convolutional Networks (GCNs) have shown strong performance in learning text representations for various tasks such as text classification, due to its expressive power in modeling graph structure data (e.g., a literature citation network). Most existing GCNs are limited to deal with documents included in a pre-defined graph, i.e., it cannot be generalized to out-of-graph documents. To address this issue, we propose to transform the document graph into a word graph, to decouple data samples (i.e., documents in training and test sets) and a GCN model by using a document-independent graph. Such word-level GCN could therefore naturally inference out-of-graph documents in an inductive way. The proposed Word-level Graph (WGraph) can not only implicitly learning word presentation with commonly-used word co-occurrences in corpora, but also incorporate extra global semantic dependency derived from inter-document relationships (e.g., literature citations). An inductive Word-grounded Graph Convolutional Network (WGCN) is proposed to learn word and document representations based on WGraph in a supervised manner. Experiments on text classification with and without citation networks evidence that the proposed WGCN model outperforms existing methods in terms of effectiveness and efficiency.