mlsanityData to 14 Oct 2026

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

arXiv 2210.10625 ↗First posted 16 Oct 2022cs.IR cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Embedded topic models are able to learn interpretable topics even with large and heavy-tailed vocabularies. However, they generally hold the Euclidean embedding space assumption, leading to a basic limitation in capturing hierarchical relations. To this end, we present a novel framework that introduces hyperbolic embeddings to represent words and topics. With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics. Furthermore, due to the superiority of hyperbolic geometry in representing hierarchical data, tree-structure knowledge can also be naturally injected to guide the learning of a topic hierarchy. Therefore, we further develop a regularization term based on the idea of contrastive learning to inject prior structural knowledge efficiently. Experiments on both topic taxonomy discovery and document representation demonstrate that the proposed framework achieves improved performance against existing embedded topic models.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 16 Oct 2022.

Builds on

32 of 62 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2016Pointer Sentinel Mixture Modelscited by 3,096
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  6. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  7. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  8. 2020Deep Graph Contrastive Representation Learningcited by 539
  9. 2016Ladder Variational Autoencoderscited by 318
  10. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
  11. 2019Topic Modeling in Embedding Spacescited by 224
  12. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
20 more
  1. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 206
  2. 2017Autoencoding Variational Inference For Topic Modelscited by 169
  3. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 162
  4. 2018Poincar'e GloVe: Hyperbolic Word Embeddingscited by 156
  5. 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
  6. 2015Neural Variational Inference for Text Processingcited by 111
  7. 2019Topic Modeling with Wasserstein Autoencoderscited by 53
  8. 2018Large-Margin Classification in Hyperbolic Spacecited by 41
  9. 2022Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddingscited by 36
  10. 2018WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modelingcited by 32
  11. 2018Improving Topic Models with Latent Feature Word Representationscited by 28
  12. 2016Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledgecited by 23
  13. 2021Sawtooth Factorial Topic Embeddings Guided Gamma Belief Networkcited by 23
  14. 2020Hierarchical Topic Mining via Joint Spherical Tree and Text Embeddingcited by 22
  15. 2020Deep Sentiment Classification and Topic Discovery on Novel Coronavirus or COVID-19 Online Discussions: NLP Using LSTM Recurrent Neural Network Approachcited by 20
  16. 2015Gamma Belief Networkscited by 19
  17. 2018Dirichlet belief networks for topic structure learningcited by 12
  18. 2017Topic Compositional Neural Language Modelcited by 11
  19. 2021TopicNet: Semantic Graph-Guided Topic Discoverycited by 9
  20. 2022Knowledge-Aware Bayesian Deep Topic Modelcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 6; 2025: 2; 2026: 1.

15 papers.

Sort:

By area:

  1. 2023Effective Neural Topic Modeling with Embedding Clustering Regularizationcited by 46
  2. 2024FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Modelcited by 35
  3. 2023Towards the TopMost: A Topic Modeling System Toolkitcited by 21
  4. 2024A Survey on Neural Topic Models: Methods, Applications, and Challengescited by 18
  5. 2024Topic Modeling as Multi-Objective Contrastive Optimizationcited by 12
  6. 2023Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labelscited by 8
  7. 2023Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifoldcited by 4
  8. 2024Self-supervised Topic Taxonomy Discovery in the Box Embedding Spacecited by 4
  9. 2024GloCOM: A Short Text Neural Topic Model via Global Clustering Contextcited by 4
  10. 2024HYDEN: Hyperbolic Density Representations for Medical Images and Reportscited by 2
  11. 2023HyHTM: Hyperbolic Geometry based Hierarchical Topic Modelscited by 1
  12. 2023Towards Generalising Neural Topical Representationscited by 1
3 more
  1. 2025Multi-Hop Reasoning for Question Answering with Hyperbolic Representationscited by 1
  2. 2026Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learningcited by 1
  3. 2025Hierarchical Graph Topic Modeling with Topic Tree-based Transformercited by 0