# Weakly-supervised Knowledge Graph Alignment with Adversarial Learning

arXiv: https://arxiv.org/abs/1907.03179 · HTML: https://mlsanity.com/paper/1907.03179/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Towards Entity Alignment in the Open World: An Unsupervised Approach](https://mlsanity.com/paper/2101.10535/) (2021)
- [Deep Reinforcement Learning for Entity Alignment](https://mlsanity.com/paper/2203.03315/) (2022)
- [An Adversarial Transfer Network for Knowledge Representation Learning](https://mlsanity.com/paper/2104.14757/) (2021)
- [What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?](https://mlsanity.com/paper/2310.07417/) (2023)
- [Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation](https://mlsanity.com/paper/2402.03025/) (2024)

## Abstract (arXiv)

This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i.e., without or with only a few aligned triplets. We propose an unsupervised framework to align the entity and relation embddings of different knowledge graphs with an adversarial learning framework. Moreover, a regularization term which maximizes the mutual information between the embeddings of different knowledge graphs is used to mitigate the problem of mode collapse when learning the alignment functions. Such a framework can be further seamlessly integrated with existing supervised methods by utilizing a limited number of aligned triples as guidance. Experimental results on multiple datasets prove the effectiveness of our proposed approach in both the unsupervised and the weakly-supervised settings.