AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

Yi.shi Xu, Dongsheng Wang, Bo Chen, Ruiying Lu, Zhibin Duan, Mingyuan Zhou

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 11 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Euclidean inner-product similarity with hyperbolic distance in SawETM (HyperMiner) (ablation)SawETM · 20NGkm-Purity: 43.36 -> 44.37Improved
replace Euclidean with hyperbolic distance in ETM (HyperETM) (ablation)ETM · 20NGkm-NMI: 37.72 -> 39.06Improved
hyperbolic embeddings in ETM at low embedding dimension (ablation)ETM · 20NG classification D=2accuracy: 19.87 -> 24.33Improved
hyperbolic embeddings in ETM at D=50 (ablation)ETM · 20NG classification D=50accuracy: 43.85 -> 44.38Improved
hyperbolic embeddings in SawETM at D=2 (ablation)SawETM · 20NG classification D=2accuracy: 16.74 -> 20.16Improved
add hyperbolic contrastive prior-knowledge loss (HyperMiner-KG) (ablation)HyperMiner · 20NGkm-Purity: 44.37 -> 45.16Improved
add hyperbolic contrastive prior-knowledge loss (HyperMiner-KG) (ablation)HyperMiner · TMNkm-NMI: 41.93 -> 42.81Improved
increase regularization coefficient lambda from 0.1 to 5 (ablation)HyperMiner-KG · 20NGkm-Purity: 43.76 -> 45.16Improved
increase regularization coefficient lambda from 5 to 10 (ablation)HyperMiner-KG · 20NGkm-Purity: 45.16 -> 44.81Hurt
use TopicNet Gaussian knowledge guidance instead of none (vs SawETM base)SawETM · 20NGkm-Purity: 43.36 -> 42.94Hurt

Later papers that compared with this method

1 later accepted paper reports HyperMiner as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy