mlsanityData to 7 Oct 2026

Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification

arXiv 2402.18825 ↗First posted 29 Feb 2024cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification due to its complex taxonomic structure. Nearly all recent HTC works focus on how the labels are structured but ignore the sub-structure of ground-truth labels according to each input text which contains fruitful label co-occurrence information. In this work, we introduce this local hierarchy with an adversarial framework. We propose a HiAdv framework that can fit in nearly all HTC models and optimize them with the local hierarchy as auxiliary information. We test on two typical HTC models and find that HiAdv is effective in all scenarios and is adept at dealing with complex taxonomic hierarchies. Further experiments demonstrate that the promotion of our framework indeed comes from the local hierarchy and the local hierarchy is beneficial for rare classes which have insufficient training data.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

26 of 34 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  4. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 253
  5. 2020InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspectivecited by 92
  6. 2022Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classificationcited by 52
  7. 2019Hierarchical Text Classification with Reinforced Label Assignmentcited by 41
  8. 2014Effective Use of Word Order for Text Categorization with Convolutional Neural Networkscited by 39
  9. 2019Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classificationcited by 35
  10. 2022HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classificationcited by 31
  11. 2019Hyperbolic Interaction Model For Hierarchical Multi-Label Classificationcited by 30
  12. 2020Neural Topic Modeling with Bidirectional Adversarial Trainingcited by 29
14 more
  1. 2021HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximizationcited by 25
  2. 2018ATM:Adversarial-neural Topic Modelcited by 23
  3. 2023HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classificationcited by 17
  4. 2019CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generationcited by 16
  5. 2021Conditional Adversarial Networks for Multi-Domain Text Classificationcited by 16
  6. 2022Exploiting Global and Local Hierarchies for Hierarchical Text Classificationcited by 15
  7. 2020ColdGANs: Taming Language GANs with Cautious Sampling Strategiescited by 12
  8. 2020Neural Topic Modeling with Cycle-Consistent Adversarial Trainingcited by 12
  9. 2020LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Networkcited by 11
  10. 2023Hierarchical Verbalizer for Few-Shot Hierarchical Text Classificationcited by 11
  11. 2022Hierarchical Multi-Label Classification of Scientific Documentscited by 10
  12. 2023Toward Adversarial Training on Contextualized Language Representationcited by 10
  13. 2023Improved Training of Mixture-of-Experts Language GANscited by 7
  14. 2022Co-Regularized Adversarial Learning for Multi-Domain Text Classificationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024Revisiting Hierarchical Text Classification: Inference and Metricscited by 7
  2. 2026Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidancecited by 0
  3. 2026Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learningcited by 0