# HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization

arXiv: https://arxiv.org/abs/2104.05220 · HTML: https://mlsanity.com/paper/2104.05220/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification](https://mlsanity.com/paper/1811.01727/) (2018)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Hierarchical Text Classification with Reinforced Label Assignment](https://mlsanity.com/paper/1908.10419/) (2019)
- [Effective Use of Word Order for Text Categorization with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1058/) (2014)
- [Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification](https://mlsanity.com/paper/1909.04176/) (2019)
- [Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification](https://mlsanity.com/paper/1906.04898/) (2019)
- [Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation](https://mlsanity.com/paper/2011.00802/) (2020)

## Built on by (most cited first, 25 of 25)

- [Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification](https://mlsanity.com/paper/2203.03825/) (2022)
- [HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification](https://mlsanity.com/paper/2204.13413/) (2022)
- [HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification](https://mlsanity.com/paper/2305.15182/) (2023)
- [Exploiting Global and Local Hierarchies for Hierarchical Text Classification](https://mlsanity.com/paper/2205.02613/) (2022)
- [Constrained Sequence-to-Tree Generation for Hierarchical Text Classification](https://mlsanity.com/paper/2204.00811/) (2022)
- [Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?](https://mlsanity.com/paper/2210.15882/) (2022)
- [Revisiting Hierarchical Text Classification: Inference and Metrics](https://mlsanity.com/paper/2410.01305/) (2024)
- [Hierarchical Text Classification As Sub-Hierarchy Sequence Generation](https://mlsanity.com/paper/2111.11104/) (2021)
- [HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification](https://mlsanity.com/paper/2402.01696/) (2024)
- [Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification](https://mlsanity.com/paper/2310.05128/) (2023)
- [Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding](https://mlsanity.com/paper/2310.11721/) (2023)
- [Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification](https://mlsanity.com/paper/2402.18825/) (2024)
- [AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction](https://mlsanity.com/paper/2310.07137/) (2023)
- [Your Extreme Multi-label Classifier is Secretly a Hierarchical Text Classifier for Free](https://mlsanity.com/paper/2411.13687/) (2024)
- [JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction](https://mlsanity.com/paper/2311.04196/) (2023)
- [Introducing Three New Benchmark Datasets for Hierarchical Text Classification](https://mlsanity.com/paper/2411.19119/) (2024)
- [LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning](https://mlsanity.com/paper/2412.16963/) (2024)
- [HiLight: A Hierarchy-aware Light Global Model with Hierarchical Local ConTrastive Learning](https://mlsanity.com/paper/2408.05786/) (2024)
- [A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification](https://mlsanity.com/paper/2501.13598/) (2025)
- [Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy](https://mlsanity.com/paper/2506.04381/) (2025)
- [Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning](https://mlsanity.com/paper/2507.04413/) (2025)
- [Combining Language and Topic Models for Hierarchical Text Classification](https://mlsanity.com/paper/2507.16490/) (2025)
- [Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance](https://mlsanity.com/paper/2601.08418/) (2026)
- [FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 System](https://mlsanity.com/paper/2603.03176/) (2026)
- [Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning](https://mlsanity.com/paper/2603.15708/) (2026)

## Abstract (arXiv)

The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. First, it correlates each text sample with all labels in the dataset which contains irrelevant information. Second, it does not consider any statistical constraint on the label representations learned by the structure encoder, while constraints for representation learning are proved to be helpful in previous work. In this paper, we propose HTCInfoMax to address these issues by introducing information maximization which includes two modules: text-label mutual information maximization and label prior matching. The first module can model the interaction between each text sample and its ground truth labels explicitly which filters out irrelevant information. The second one encourages the structure encoder to learn better representations with desired characteristics for all labels which can better handle label imbalance in hierarchical text classification. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed HTCInfoMax.