# HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning

arXiv: https://arxiv.org/abs/2109.10500 · HTML: https://mlsanity.com/paper/2109.10500/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 30 of 31)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Hyperbolic Neural Networks](https://mlsanity.com/paper/1805.09112/) (2018)
- [Hyperbolic Graph Convolutional Neural Networks](https://mlsanity.com/paper/1910.12933/) (2019)
- [Hyperbolic Graph Neural Networks](https://mlsanity.com/paper/1910.12892/) (2019)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Poincar'e GloVe: Hyperbolic Word Embeddings](https://mlsanity.com/paper/1810.06546/) (2018)
- [Hyperbolic Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.04562/) (2021)
- [Multi-relational Poincar'e Graph Embeddings](https://mlsanity.com/paper/1905.09791/) (2019)
- [Hyperbolic Attention Networks](https://mlsanity.com/paper/1805.09786/) (2018)
- [Geoopt: Riemannian Optimization in PyTorch](https://mlsanity.com/paper/2005.02819/) (2020)
- [Constant Curvature Graph Convolutional Networks](https://mlsanity.com/paper/1911.05076/) (2019)
- [Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks](https://mlsanity.com/paper/2012.08492/) (2020)
- [Embedding Text in Hyperbolic Spaces](https://mlsanity.com/paper/1806.04313/) (2018)
- [Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings](https://mlsanity.com/paper/1902.00913/) (2019)
- [Learning the Predictability of the Future](https://mlsanity.com/paper/2101.01600/) (2021)
- [TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network](https://mlsanity.com/paper/2001.09522/) (2020)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [Knowledge Association with Hyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2010.02162/) (2020)
- [Hyperbolic Interaction Model For Hierarchical Multi-Label Classification](https://mlsanity.com/paper/1905.10802/) (2019)
- [HyperText: Endowing FastText with Hyperbolic Geometry](https://mlsanity.com/paper/2010.16143/) (2020)
- [Improving Hypernymy Detection with an Integrated Path-based and Distributional Method](https://mlsanity.com/paper/1603.06076/) (2016)
- [Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings](https://mlsanity.com/paper/1906.02002/) (2019)
- [A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification](https://mlsanity.com/paper/2010.02053/) (2020)
- [Self-Attention with Structural Position Representations](https://mlsanity.com/paper/1909.00383/) (2019)
- [Taxonomy Completion via Triplet Matching Network](https://mlsanity.com/paper/2101.01896/) (2021)
- [Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2101.11268/) (2021)
- [MetaPAD: Meta Pattern Discovery from Massive Text Corpora](https://mlsanity.com/paper/1703.04213/) (2017)

## Built on by (most cited first, 14 of 14)

- [DICE: Data-Efficient Clinical Event Extraction with Generative Models](https://mlsanity.com/paper/2208.07989/) (2022)
- [Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?](https://mlsanity.com/paper/2212.10784/) (2022)
- [Ontology Embedding: A Survey of Methods, Applications and Resources](https://mlsanity.com/paper/2406.10964/) (2024)
- [Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction](https://mlsanity.com/paper/2501.17326/) (2025)
- [Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision](https://mlsanity.com/paper/2203.14921/) (2022)
- [Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces](https://mlsanity.com/paper/2209.05635/) (2022)
- [Insert or Attach: Taxonomy Completion via Box Embedding](https://mlsanity.com/paper/2305.11004/) (2023)
- [Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection](https://mlsanity.com/paper/2501.17338/) (2025)
- [Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies](https://mlsanity.com/paper/2505.12404/) (2025)
- [Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning](https://mlsanity.com/paper/2605.00265/) (2026)
- [DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space](https://mlsanity.com/paper/2302.11165/) (2023)
- [Towards Visual Taxonomy Expansion](https://mlsanity.com/paper/2309.06105/) (2023)
- [FoodTaxo: Generating Food Taxonomies with Large Language Models](https://mlsanity.com/paper/2505.19838/) (2025)
- [COntExt: Towards Context-Aware Ontology Extension from Operational Metrics](https://mlsanity.com/paper/2607.29553/) (2026)

## Abstract (arXiv)

Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on unseen concepts during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.