TextRGNN: Residual Graph Neural Networks for Text Classification
This work addresses text classification, a key task in natural language processing, by enhancing graph neural networks, but it appears incremental as it builds on existing GNN paradigms with specific modifications.
The paper tackles text classification by proposing TextRGNN, an improved graph neural network structure that uses residual connections to deepen the network and integrates a probabilistic language model for node embedding initialization, resulting in state-of-the-art performance on various datasets with significant accuracy improvements.
Recently, text classification model based on graph neural network (GNN) has attracted more and more attention. Most of these models adopt a similar network paradigm, that is, using pre-training node embedding initialization and two-layer graph convolution. In this work, we propose TextRGNN, an improved GNN structure that introduces residual connection to deepen the convolution network depth. Our structure can obtain a wider node receptive field and effectively suppress the over-smoothing of node features. In addition, we integrate the probabilistic language model into the initialization of graph node embedding, so that the non-graph semantic information of can be better extracted. The experimental results show that our model is general and efficient. It can significantly improve the classification accuracy whether in corpus level or text level, and achieve SOTA performance on a wide range of text classification datasets.