We consider the problem of learning efficient and inductive graph
convolutional networks for text classification with a large number of examples
and features. Existing state-of-the-art graph embedding based methods such as
predictive text embedding (PTE) and TextGCN have shortcomings in terms of
predictive performance, scalability and inductive capability. To address these
limitations, we propose a heterogeneous graph convolutional network (HeteGCN)
modeling approach that unites the best aspects of PTE and TextGCN together. The
main idea is to learn feature embeddings and derive document embeddings using a
HeteGCN architecture with different graphs used across layers. We simplify
TextGCN by dissecting into several HeteGCN models which (a) helps to study the
usefulness of individual models and (b) offers flexibility in fusing learned
embeddings from different models. In effect, the number of model parameters is
reduced significantly, enabling faster training and improving performance in
small labeled training set scenario. Our detailed experimental studies
demonstrate the efficacy of the proposed approach.

本文提出了一种异构图卷积网络建模方法 HeteGCN，结合了 predictive text embedding (PTE) 和 TextGCN 的优点用于文本分类，以解决现有方法预测能力、可扩展性和归纳能力的局限性。通过使用不同的图层在一个 HeteGCN 架构中学习特征嵌入并派生文档嵌入，将 TextGCN 简化为几个 HeteGCN 模型，从而简化了模型参数，以提高性能和训练速度。实验结果表明所提出的方法在小的标注训练集方案下有效。