# Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification

arXiv: https://arxiv.org/abs/2112.06386 · HTML: https://mlsanity.com/paper/2112.06386/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Recurrent Neural Network for Text Classification with Multi-Task Learning](https://mlsanity.com/paper/1605.05101/) (2016)
- [Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks](https://mlsanity.com/paper/2004.13826/) (2020)
- [Be More with Less: Hypergraph Attention Networks for Inductive Text Classification](https://mlsanity.com/paper/2011.00387/) (2020)
- [Text Level Graph Neural Network for Text Classification](https://mlsanity.com/paper/1910.02356/) (2019)
- [Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms](https://mlsanity.com/paper/1805.09843/) (2018)
- [Tensor Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2001.05313/) (2020)
- [Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification](https://mlsanity.com/paper/1906.04898/) (2019)

## Built on by (most cited first, 15 of 15)

- [Graph Neural Networks for Text Classification: A Survey](https://mlsanity.com/paper/2304.11534/) (2023)
- [PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning](https://mlsanity.com/paper/2406.17923/) (2024)
- [Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework](https://mlsanity.com/paper/2301.00489/) (2023)
- [DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification](https://mlsanity.com/paper/2307.09813/) (2023)
- [Improving out-of-distribution generalization in graphs via hierarchical semantic environments](https://mlsanity.com/paper/2403.01773/) (2024)
- [FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores](https://mlsanity.com/paper/2412.11007/) (2024)
- [Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning](https://mlsanity.com/paper/2305.09756/) (2023)
- [Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning](https://mlsanity.com/paper/2512.20094/) (2025)
- [Are We Really Making Much Progress in Text Classification? A Comparative Review](https://mlsanity.com/paper/2204.03954/) (2022)
- [Hybrid Quantum Graph Neural Network for Molecular Property Prediction](https://mlsanity.com/paper/2405.05205/) (2024)
- [SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome](https://mlsanity.com/paper/2511.15464/) (2025)
- [DocNet: Semantic Structure in Inductive Bias Detection Models](https://mlsanity.com/paper/2406.10965/) (2024)
- [Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification](https://mlsanity.com/paper/2407.10105/) (2024)
- [Graph Neural Networks on Discriminative Graphs of Words](https://mlsanity.com/paper/2410.20469/) (2024)
- [A Novel Graph-Sequence Learning Model for Inductive Text Classification](https://mlsanity.com/paper/2512.20097/) (2025)

## Abstract (arXiv)

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 generated by a disjoint union of sentence-level word co-occurrence graphs. Our model collects a set of trainable edges connecting disjoint words between sentences and employs structure learning to sparsely select edges with dynamic contextual dependencies. Graphs with sparse structures can jointly exploit local and global contextual information in documents through GNNs. For inductive learning, the refined document graph is further fed into a general readout function for graph-level classification and optimization in an end-to-end manner. Extensive experiments on several real-world datasets demonstrate that the proposed model outperforms most state-of-the-art results, and reveal the necessity to learn sparse structures for each document.