Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification

@article{Piao2022SparseSL,
  title={Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification},
  author={Yinhua Piao and Sangseon Lee and Dohoon Lee and Sun Kim},
  journal={ArXiv},
  year={2022},
  volume={abs/2112.06386}
}
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word ambiguity, (2) word synonymity, and (3) dynamic contextual dependency. To address these challenges, we propose a novel GNN-based sparse structure learning model for inductive document classification. Specifically, a document-level graph is initially… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 45 REFERENCES
Learning Dynamic Hierarchical Topic Graph with Graph Convolutional Network for Document Classification
TLDR
A probabilistic deep topic model is integrated into graph construction, and a novel trainable hierarchical topic graph (HTG) is proposed, including word-level, hierarchical topic-level and document-level nodes, exhibiting semantic variation from finegrained to coarse.
Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
TLDR
This work proposes TextING for inductive text classification via GNN, which first builds individual graphs for each document and then uses GNN to learn the fine-grained word representations based on their local structure, which can also effectively produce embeddings for unseen words in the new document.
Graph Convolutional Networks for Text Classification
TLDR
This work builds a single text graph for a corpus based on word co-occurrence and document word relations, then learns a Text Graph Convolutional Network (Text GCN) for the corpus, which jointly learns the embeddings for both words and documents as supervised by the known class labels for documents.
Tensor Graph Convolutional Networks for Text Classification
TLDR
This paper investigates graph-based neural networks for text classification problem with a new framework TensorGCN (tensor graph convolutional networks), which presents an effective way to harmonize and integrate heterogeneous information from different kinds of graphs.
Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN
TLDR
A graph-CNN based deep learning model is proposed to first convert texts to graph-of-words, and then use graph convolution operations to convolve the word graph and regularize the deep architecture with the dependency among labels.
A Comprehensive Survey on Graph Neural Networks
TLDR
This article provides a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields and proposes a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNS, convolutional GNN’s, graph autoencoders, and spatial–temporal Gnns.
Text Level Graph Neural Network for Text Classification
TLDR
This work proposes a new GNN based model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus, which removes the burden of dependence between an individual text and entire corpus which support online testing, but still preserve global information.
Graph Attention Networks
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior
Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification
TLDR
This paper proposes a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework that significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.
Inductive Representation Learning on Large Graphs
TLDR
GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
...
...