# Insert or Attach: Taxonomy Completion via Box Embedding

arXiv: https://arxiv.org/abs/2305.11004 · HTML: https://mlsanity.com/paper/2305.11004/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks](https://mlsanity.com/paper/1909.09586/) (2019)
- [Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures](https://mlsanity.com/paper/1805.06627/) (2018)
- [Modeling Fine-Grained Entity Types with Box Embeddings](https://mlsanity.com/paper/2101.00345/) (2021)
- [Temporal Knowledge Graph Completion using Box Embeddings](https://mlsanity.com/paper/2109.08970/) (2021)
- [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)
- [TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations](https://mlsanity.com/paper/2202.04887/) (2022)
- [Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations](https://mlsanity.com/paper/2106.02974/) (2021)
- [Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings](https://mlsanity.com/paper/2008.05785/) (2020)
- [HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning](https://mlsanity.com/paper/2109.10500/) (2021)
- [Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings](https://mlsanity.com/paper/2106.14361/) (2021)
- [Box Embeddings: An open-source library for representation learning using geometric structures](https://mlsanity.com/paper/2109.04997/) (2021)
- [Technical Question Answering across Tasks and Domains](https://mlsanity.com/paper/2010.09780/) (2020)

## Built on by (most cited first, 1 of 1)

- [TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2601.09633/) (2026)

## Abstract (arXiv)

Taxonomy completion, enriching existing taxonomies by inserting new concepts as parents or attaching them as children, has gained significant interest. Previous approaches embed concepts as vectors in Euclidean space, which makes it difficult to model asymmetric relations in taxonomy. In addition, they introduce pseudo-leaves to convert attachment cases into insertion cases, leading to an incorrect bias in network learning dominated by numerous pseudo-leaves. Addressing these, our framework, TaxBox, leverages box containment and center closeness to design two specialized geometric scorers within the box embedding space. These scorers are tailored for insertion and attachment operations and can effectively capture intrinsic relationships between concepts by optimizing on a granular box constraint loss. We employ a dynamic ranking loss mechanism to balance the scores from these scorers, allowing adaptive adjustments of insertion and attachment scores. Experiments on four real-world datasets show that TaxBox significantly outperforms previous methods, yielding substantial improvements over prior methods in real-world datasets, with average performance boosts of 6.7%, 34.9%, and 51.4% in MRR, Hit@1, and Prec@1, respectively.