# ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions

arXiv: https://arxiv.org/abs/1904.12694 · HTML: https://mlsanity.com/paper/1904.12694/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks](https://mlsanity.com/paper/2105.08621/) (2021)
- [DINE: Dimensional Interpretability of Node Embeddings](https://mlsanity.com/paper/2310.01162/) (2023)
- [Privacy and Transparency in Graph Machine Learning: A Unified Perspective](https://mlsanity.com/paper/2207.10896/) (2022)
- [Learnt Sparsification for Interpretable Graph Neural Networks](https://mlsanity.com/paper/2106.12920/) (2021)
- [Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples](https://mlsanity.com/paper/2212.02651/) (2022)
- [KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation](https://mlsanity.com/paper/2310.01065/) (2023)
- [DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network](https://mlsanity.com/paper/2408.12139/) (2024)
- [Adversarial Robustness of Probabilistic Network Embedding for Link Prediction](https://mlsanity.com/paper/2107.01936/) (2021)
- [Controllable Edge-Type-Specific Interpretation in Multi-Relational Graph Neural Networks for Drug Response Prediction](https://mlsanity.com/paper/2408.17129/) (2024)

## Abstract (arXiv)

Networks are powerful data structures, but are challenging to work with for conventional machine learning methods. Network Embedding (NE) methods attempt to resolve this by learning vector representations for the nodes, for subsequent use in downstream machine learning tasks. Link Prediction (LP) is one such downstream machine learning task that is an important use case and popular benchmark for NE methods. Unfortunately, while NE methods perform exceedingly well at this task, they are lacking in transparency as compared to simpler LP approaches. We introduce ExplaiNE, an approach to offer counterfactual explanations for NE-based LP methods, by identifying existing links in the network that explain the predicted links. ExplaiNE is applicable to a broad class of NE algorithms. An extensive empirical evaluation for the NE method `Conditional Network Embedding' in particular demonstrates its accuracy and scalability.