# Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases

arXiv: https://arxiv.org/abs/2203.05744 · HTML: https://mlsanity.com/paper/2203.05744/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [Improving GANs Using Optimal Transport](https://mlsanity.com/paper/1803.05573/) (2018)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/1908.08210/) (2019)
- [Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences](https://mlsanity.com/paper/1902.06236/) (2019)
- [Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network](https://mlsanity.com/paper/1905.11605/) (2019)
- [CODER: Knowledge infused cross-lingual medical term embedding for term normalization](https://mlsanity.com/paper/2011.02947/) (2020)
- [Relational Reflection Entity Alignment](https://mlsanity.com/paper/2008.07962/) (2020)
- [Improved Neural Relation Detection for Knowledge Base Question Answering](https://mlsanity.com/paper/1704.06194/) (2017)
- [Improving Sequence-to-Sequence Learning via Optimal Transport](https://mlsanity.com/paper/1901.06283/) (2019)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [RAGA: Relation-aware Graph Attention Networks for Global Entity Alignment](https://mlsanity.com/paper/2103.00791/) (2021)
- [Adversarial Text Generation via Feature-Mover's Distance](https://mlsanity.com/paper/1809.06297/) (2018)
- [From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment](https://mlsanity.com/paper/2109.02363/) (2021)
- [Relation-Aware Neighborhood Matching Model for Entity Alignment](https://mlsanity.com/paper/2012.08128/) (2020)
- [Knowing the No-match: Entity Alignment with Dangling Cases](https://mlsanity.com/paper/2106.02248/) (2021)
- [Predicting Completeness in Knowledge Bases](https://mlsanity.com/paper/1612.05786/) (2016)
- [Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment](https://mlsanity.com/paper/2001.08728/) (2020)
- [An Industry Evaluation of Embedding-based Entity Alignment](https://mlsanity.com/paper/2010.11522/) (2020)
- [Towards Entity Alignment in the Open World: An Unsupervised Approach](https://mlsanity.com/paper/2101.10535/) (2021)
- [A Self-supervised Method for Entity Alignment](https://mlsanity.com/paper/2106.09395/) (2021)
- [EchoEA: Echo Information between Entities and Relations for Entity Alignment](https://mlsanity.com/paper/2107.03054/) (2021)

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

- [Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases](https://mlsanity.com/paper/2403.10978/) (2024)
- [Investigating Graph Structure Information for Entity Alignment with Dangling Cases](https://mlsanity.com/paper/2304.04718/) (2023)

## Abstract (arXiv)

Entity alignment (EA) merges knowledge graphs (KGs) by identifying the equivalent entities in different graphs, which can effectively enrich knowledge representations of KGs. However, in practice, different KGs often include dangling entities whose counterparts cannot be found in the other graph, which limits the performance of EA methods. To improve EA with dangling entities, we propose an unsupervised method called Semi-constraint Optimal Transport for Entity Alignment in Dangling cases (SoTead). Our main idea is to model the entity alignment between two KGs as an optimal transport problem from one KG's entities to the others. First, we set pseudo entity pairs between KGs based on pretrained word embeddings. Then, we conduct contrastive metric learning to obtain the transport cost between each entity pair. Finally, we introduce a virtual entity for each KG to "align" the dangling entities from the other KGs, which relaxes the optimization constraints and leads to a semi-constraint optimal transport. In the experimental part, we first show the superiority of SoTead on a commonly-used entity alignment dataset. Besides, to analyze the ability for dangling entity detection with other baselines, we construct a medical cross-lingual knowledge graph dataset, MedED, where our SoTead also reaches state-of-the-art performance.