# Reimagining GNN Explanations with ideas from Tabular Data

arXiv: https://arxiv.org/abs/2106.12665 · HTML: https://mlsanity.com/paper/2106.12665/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 23 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Link Prediction using Graph Neural Networks for Master Data Management](https://mlsanity.com/paper/2003.04732/) (2020)
- [Explainable Link Prediction for Privacy-Preserving Contact Tracing](https://mlsanity.com/paper/2012.05516/) (2020)
- [Data Augmentation for Personal Knowledge Base Population](https://mlsanity.com/paper/2002.10943/) (2020)
- [Towards Automated Evaluation of Explanations in Graph Neural Networks](https://mlsanity.com/paper/2106.11864/) (2021)

## Built on by (most cited first, 1 of 1)

- [xEM: Explainable Entity Matching in Customer 360](https://mlsanity.com/paper/2212.00342/) (2022)

## Abstract (arXiv)

Explainability techniques for Graph Neural Networks still have a long way to go compared to explanations available for both neural and decision decision tree-based models trained on tabular data. Using a task that straddles both graphs and tabular data, namely Entity Matching, we comment on key aspects of explainability that are missing in GNN model explanations.