InducT-GCN: Inductive Graph Convolutional Networks for Text Classification

Anonymous

Abstract: Text classification aims to assign labels to textual units by making use of global information. Recent studies have applied graph neural network (GNN) techniques to capture the global word co-occurrence in a corpus. Most existing approaches require that all the nodes (training and test) in a graph are present during training, which are transductive and do not naturally generalise to unseen nodes. To make those models \textit{inductive}, previous works use extra resources, like pretrained word embedding. However, high-quality resource is not always available and can be hard to train. Under the extreme settings with no extra resource and limited amount of training set, can we still learn an inductive graph-based text classification model? In this paper, we introduce a novel inductive graph-based text classification framework, namely InducT-GCN (InducTive Graph Convolutional Networks for Text classification). Compared to transductive models that require test documents in training, we construct a graph based on the statistics of training documents only and represent document vectors with a weighted sum of word vectors. We then conduct one-directional GCN propagation during testing. Across five text classification benchmarks, our InducT-GCN outperformed state-of-the-art methods that are either transductive in nature or pre-trained additional resources. We also conducted scalability testing by gradually increasing the data size and revealed that our InducT-GCN can reduce the time and space complexity.