mlsanityData to 14 Oct 2026

A Novel Graph-Sequence Learning Model for Inductive Text Classification

arXiv 2512.20097 ↗First posted 23 Dec 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Text classification plays an important role in various downstream text-related tasks, such as sentiment analysis, fake news detection, and public opinion analysis. Recently, text classification based on Graph Neural Networks (GNNs) has made significant progress due to their strong capabilities of structural relationship learning. However, these approaches still face two major limitations. First, these approaches fail to fully consider the diverse structural information across word pairs, e.g., co-occurrence, syntax, and semantics. Furthermore, they neglect sequence information in the text graph structure information learning module and can not classify texts with new words and relations. In this paper, we propose a Novel Graph-Sequence Learning Model for Inductive Text Classification (TextGSL) to address the previously mentioned issues. More specifically, we construct a single text-level graph for all words in each text and establish different edge types based on the diverse relationships between word pairs. Building upon this, we design an adaptive multi-edge message-passing paradigm to aggregate diverse structural information between word pairs. Additionally, sequential information among text data can be captured by the proposed TextGSL through the incorporation of Transformer layers. Therefore, TextGSL can learn more discriminative text representations. TextGSL has been comprehensively compared with several strong baselines. The experimental results on diverse benchmarking datasets demonstrate that TextGSL outperforms these baselines in terms of accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 57 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

23 of 57 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2015Gated Graph Sequence Neural Networkscited by 796
  9. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 505
  10. 2018Graph Convolutional Networks for Text Classificationcited by 345
  11. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  12. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
11 more
  1. 2020Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networkscited by 77
  2. 2020Be More with Less: Hypergraph Attention Networks for Inductive Text Classificationcited by 74
  3. 2021BertGCN: Transductive Text Classification by Combining GCN and BERTcited by 74
  4. 2019Text Level Graph Neural Network for Text Classificationcited by 60
  5. 2020Tensor Graph Convolutional Networks for Text Classificationcited by 49
  6. 2016Gated-Attention Readers for Text Comprehensioncited by 37
  7. 2021Learning Conjoint Attentions for Graph Neural Netscited by 26
  8. 2021Sparse Structure Learning via Graph Neural Networks for Inductive Document Classificationcited by 15
  9. 2022InducT-GCN: Inductive Graph Convolutional Networks for Text Classificationcited by 15
  10. 2022Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learningcited by 6
  11. 2021An Intelligent Question Answering System based on Power Knowledge Graphcited by 4

Built on by

Not cited yet.