# i-Align: an interpretable knowledge graph alignment model

arXiv: https://arxiv.org/abs/2308.13755 · HTML: https://mlsanity.com/paper/2308.13755/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 26 Aug 2023.

## Builds on (most cited first, 30 of 33)

- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [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)
- [Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation](https://mlsanity.com/paper/1911.08936/) (2019)
- [GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings](https://mlsanity.com/paper/2106.05609/) (2021)
- [Multi-Channel Graph Neural Network for Entity Alignment](https://mlsanity.com/paper/1908.09898/) (2019)
- [Multi-view Knowledge Graph Embedding for Entity Alignment](https://mlsanity.com/paper/1906.02390/) (2019)
- [Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network](https://mlsanity.com/paper/1905.11605/) (2019)
- [Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment](https://mlsanity.com/paper/2010.03249/) (2020)
- [Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment](https://mlsanity.com/paper/1806.06478/) (2018)
- [Neighborhood Matching Network for Entity Alignment](https://mlsanity.com/paper/2005.05607/) (2020)
- [TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs](https://mlsanity.com/paper/2004.13579/) (2020)
- [Interpretability via Model Extraction](https://mlsanity.com/paper/1706.09773/) (2017)
- [Jointly Learning Entity and Relation Representations for Entity Alignment](https://mlsanity.com/paper/1909.09317/) (2019)

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

- [Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning](https://mlsanity.com/paper/2505.13994/) (2025)
- [NAEx: A Plug-and-Play Framework for Explaining Network Alignment](https://mlsanity.com/paper/2508.04731/) (2025)

## Abstract (arXiv)

Knowledge graphs (KGs) are becoming essential resources for many downstream applications. However, their incompleteness may limit their potential. Thus, continuous curation is needed to mitigate this problem. One of the strategies to address this problem is KG alignment, i.e., forming a more complete KG by merging two or more KGs. This paper proposes i-Align, an interpretable KG alignment model. Unlike the existing KG alignment models, i-Align provides an explanation for each alignment prediction while maintaining high alignment performance. Experts can use the explanation to check the correctness of the alignment prediction. Thus, the high quality of a KG can be maintained during the curation process (e.g., the merging process of two KGs). To this end, a novel Transformer-based Graph Encoder (Trans-GE) is proposed as a key component of i-Align for aggregating information from entities' neighbors (structures). Trans-GE uses Edge-gated Attention that combines the adjacency matrix and the self-attention matrix to learn a gating mechanism to control the information aggregation from the neighboring entities. It also uses historical embeddings, allowing Trans-GE to be trained over mini-batches, or smaller sub-graphs, to address the scalability issue when encoding a large KG. Another component of i-Align is a Transformer encoder for aggregating entities' attributes. This way, i-Align can generate explanations in the form of a set of the most influential attributes/neighbors based on attention weights. Extensive experiments are conducted to show the power of i-Align. The experiments include several aspects, such as the model's effectiveness for aligning KGs, the quality of the generated explanations, and its practicality for aligning large KGs. The results show the effectiveness of i-Align in these aspects.