# TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion

arXiv: https://arxiv.org/abs/2601.09633 · HTML: https://mlsanity.com/paper/2601.09633/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings](https://mlsanity.com/paper/2002.05969/) (2020)
- [Word Representations via Gaussian Embedding](https://mlsanity.com/paper/1412.6623/) (2014)
- [Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures](https://mlsanity.com/paper/1805.06627/) (2018)
- [Improving Local Identifiability in Probabilistic Box Embeddings](https://mlsanity.com/paper/2010.04831/) (2020)
- [HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion](https://mlsanity.com/paper/1910.08194/) (2019)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [Probabilistic FastText for Multi-Sense Word Embeddings](https://mlsanity.com/paper/1806.02901/) (2018)
- [AliCoCo: Alibaba E-commerce Cognitive Concept Net](https://mlsanity.com/paper/2003.13230/) (2020)
- [Octet: Online Catalog Taxonomy Enrichment with Self-Supervision](https://mlsanity.com/paper/2006.10276/) (2020)
- [Taxonomy Completion via Triplet Matching Network](https://mlsanity.com/paper/2101.01896/) (2021)
- [TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations](https://mlsanity.com/paper/2202.04887/) (2022)
- [CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring](https://mlsanity.com/paper/2010.06714/) (2020)
- [Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2101.11268/) (2021)
- [Multimodal Word Distributions](https://mlsanity.com/paper/1704.08424/) (2017)
- [Box Embeddings: An open-source library for representation learning using geometric structures](https://mlsanity.com/paper/2109.04997/) (2021)
- [Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion](https://mlsanity.com/paper/2505.13282/) (2025)
- [Producing Usable Taxonomies Cheaply and Rapidly at Pinterest Using Discovered Dynamic μ-Topics](https://mlsanity.com/paper/2301.12520/) (2023)
- [Insert or Attach: Taxonomy Completion via Box Embedding](https://mlsanity.com/paper/2305.11004/) (2023)

## Built on by (most cited first, 2 of 2)

- [Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning](https://mlsanity.com/paper/2605.00265/) (2026)
- [Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique](https://mlsanity.com/paper/2608.20777/) (2026)

## Abstract (arXiv)

Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce and semantic search. Yet, manual taxonomy expansion is labor-intensive and slow. Existing methods rely on point-based vector embeddings, which model symmetric similarity and thus struggle with the asymmetric relationships that are fundamental to taxonomies. Box embeddings offer a promising alternative by enabling containment and disjointness, but they face key issues: (i) unstable gradients at the intersection boundaries, (ii) no notion of semantic uncertainty, and (iii) limited capacity to represent polysemy or ambiguity. We address these shortcomings with TaxoBell, a Gaussian box embedding framework that translates between box geometries and multivariate Gaussian distributions, where means encode semantic location and covariances encode uncertainty. Energy-based optimization yields stable optimization, robust modeling of ambiguous concepts, and interpretable hierarchical reasoning. Extensive experiments on five benchmark datasets demonstrate that TaxoBell significantly outperforms eight state-of-the-art taxonomy expansion baselines by 19% in MRR and around 25% in Recall@k. We further demonstrate the advantages and pitfalls of TaxoBell with error analysis and ablation studies.