Heterogeneous Graph Attention Networks for Semi …

els the documents, words and labels with graphs and learns text (node) embeddings for classifi-cation. Meng et al. (2018) leveraged seed in-formation to generate pseudo-labeled documents for pre-training. Yin et al. (2015) used a semi-supervised learning method based on SVM to la-bel the unlabeled documents in an iterative way.

  Document, Labeled, Unlabeled, Labeled documents, Unlabeled documents