mlsanityData to 7 Oct 2026

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

arXiv 2004.13826 ↗First posted 22 Apr 2020cs.CLcited by 77

Not on the map. Why?

Abstract (arXiv)

Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. In this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 22; 2023: 13; 2024: 14; 2025: 9; 2026: 2.

77 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 153
  3. 2023SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learningcited by 73
  4. 2022Multimodal learning with graphscited by 54
  5. 2021Dynamic Graph Collaborative Filteringcited by 33
  6. 2021ReGVD: Revisiting Graph Neural Networks for Vulnerability Detectioncited by 32
  7. 2022Distributed Graph Neural Network Training: A Surveycited by 32
  8. 2022Evidence-aware Fake News Detection with Graph Neural Networkscited by 30
  9. 2021Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practicescited by 24
  10. 2022MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platformscited by 16
  11. 2023Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Modelscited by 16
  12. 2021Sparse Structure Learning via Graph Neural Networks for Inductive Document Classificationcited by 15
38 more
  1. 2022InducT-GCN: Inductive Graph Convolutional Networks for Text Classificationcited by 15
  2. 2023Graph Neural Networks for Text Classification: A Surveycited by 15
  3. 2021Hierarchical Heterogeneous Graph Representation Learning for Short Text Classificationcited by 13
  4. 2021Cross-lingual Text Classification with Heterogeneous Graph Neural Networkcited by 12
  5. 2021Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networkscited by 11
  6. 2022Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasetscited by 11
  7. 2021Relation-aware Heterogeneous Graph for User Profilingcited by 9
  8. 2022Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networkscited by 9
  9. 2024Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classificationcited by 8
  10. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7
  11. 2022Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networkscited by 7
  12. 2023Search to Capture Long-range Dependency with Stacking GNNs for Graph Classificationcited by 7
  13. 2023State of the Art and Potentialities of Graph-level Learningcited by 6
  14. 2024DocGraphLM: Documental Graph Language Model for Information Extractioncited by 6
  15. 2025Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairscited by 6
  16. 2021Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolutioncited by 5
  17. 2023An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graphcited by 5
  18. 2024Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systemscited by 5
  19. 2022Incorporating Heterophily into Graph Neural Networks for Graph Classificationcited by 4
  20. 2022Understanding Graph Convolutional Networks for Text Classificationcited by 4
  21. 2022Visualizing and Explaining Language Modelscited by 4
  22. 2024A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Taskscited by 4
  23. 2025SciClaimHunt: A Large Dataset for Evidence-based Scientific Claim Verificationcited by 4
  24. 2022Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networkscited by 3
  25. 2022Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Languagecited by 3
  26. 2021Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotationscited by 2
  27. 2021Hierarchical information matters: Text classification via tree based graph neural networkcited by 2
  28. 2022Enhancing Graph Contrastive Learning with Node Similaritycited by 2
  29. 2022On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processingcited by 2
  30. 2023Seq-HyGAN: Sequence Classification via Hypergraph Attention Networkcited by 2
  31. 2023Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learningcited by 2
  32. 2023Explainable Identification of Hate Speech towards Islam using Graph Neural Networkscited by 2
  33. 2024Style-News: Incorporating Stylized News Generation and Adversarial Verification for Neural Fake News Detectioncited by 2
  34. 2025Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Informationcited by 2
  35. 2021Graph Convolutional Network with Generalized Factorized Bilinear Aggregationcited by 1
  36. 2021TextRGNN: Residual Graph Neural Networks for Text Classificationcited by 1
  37. 2022Are We Really Making Much Progress in Text Classification? A Comparative Reviewcited by 1
  38. 2022TeKo: Text-Rich Graph Neural Networks with External Knowledgecited by 1

50 most cited of 77 All 77 (JSON)