# Improving Knowledge Graph Entity Alignment with Graph Augmentation

arXiv: https://arxiv.org/abs/2304.14585 · HTML: https://mlsanity.com/paper/2304.14585/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 28 Apr 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs](https://mlsanity.com/paper/2003.07743/) (2020)
- [Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/1908.08210/) (2019)
- [Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation](https://mlsanity.com/paper/1911.08936/) (2019)
- [Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs](https://mlsanity.com/paper/1905.04914/) (2019)
- [Multi-view Knowledge Graph Embedding for Entity Alignment](https://mlsanity.com/paper/1906.02390/) (2019)
- [Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment](https://mlsanity.com/paper/2010.03249/) (2020)
- [Aligning Cross-Lingual Entities with Multi-Aspect Information](https://mlsanity.com/paper/1910.06575/) (2019)
- [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning](https://mlsanity.com/paper/2009.07111/) (2020)
- [Knowledge Association with Hyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2010.02162/) (2020)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [Informed Multi-context Entity Alignment](https://mlsanity.com/paper/2201.00304/) (2022)

## Built on by (most cited first, 3 of 3)

- [Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning](https://mlsanity.com/paper/2412.05028/) (2024)
- [Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning](https://mlsanity.com/paper/2412.00881/) (2024)
- [MixTEA: Semi-supervised Entity Alignment with Mixture Teaching](https://mlsanity.com/paper/2311.04441/) (2023)

## Abstract (arXiv)

Entity alignment (EA) which links equivalent entities across different knowledge graphs (KGs) plays a crucial role in knowledge fusion. In recent years, graph neural networks (GNNs) have been successfully applied in many embedding-based EA methods. However, existing GNN-based methods either suffer from the structural heterogeneity issue that especially appears in the real KG distributions or ignore the heterogeneous representation learning for unseen (unlabeled) entities, which would lead the model to overfit on few alignment seeds (i.e., training data) and thus cause unsatisfactory alignment performance. To enhance the EA ability, we propose GAEA, a novel EA approach based on graph augmentation. In this model, we design a simple Entity-Relation (ER) Encoder to generate latent representations for entities via jointly modeling comprehensive structural information and rich relation semantics. Moreover, we use graph augmentation to create two graph views for margin-based alignment learning and contrastive entity representation learning, thus mitigating structural heterogeneity and further improving the model's alignment performance. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of our method.