# Forget and Explain: Transparent Verification of GNN Unlearning

arXiv: https://arxiv.org/abs/2512.07450 · HTML: https://mlsanity.com/paper/2512.07450/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks](https://mlsanity.com/paper/2407.19398/) (2024)
- [Unlink to Unlearn: Simplifying Edge Unlearning in GNNs](https://mlsanity.com/paper/2402.10695/) (2024)
- [Verifying Machine Unlearning with Explainable AI](https://mlsanity.com/paper/2411.13332/) (2024)

## Abstract (arXiv)

Graph neural networks (GNNs) are increasingly used to model complex patterns in graph-structured data. However, enabling them to "forget" designated information remains challenging, especially under privacy regulations such as the GDPR. Existing unlearning methods largely optimize for efficiency and scalability, yet they offer little transparency, and the black-box nature of GNNs makes it difficult to verify whether forgetting has truly occurred. We propose an explainability-driven verifier for GNN unlearning that snapshots the model before and after deletion, using attribution shifts and localized structural changes (for example, graph edit distance) as transparent evidence. The verifier uses five explainability metrics: residual attribution, heatmap shift, explainability score deviation, graph edit distance, and a diagnostic graph rule shift. We evaluate two backbones (GCN, GAT) and four unlearning strategies (Retrain, GraphEditor, GNNDelete, IDEA) across five benchmarks (Cora, Citeseer, Pubmed, Coauthor-CS, Coauthor-Physics). Results show that Retrain and GNNDelete achieve near-complete forgetting, GraphEditor provides partial erasure, and IDEA leaves residual signals. These explanation deltas provide the primary, human-readable evidence of forgetting; we also report membership-inference ROC-AUC as a complementary, graph-wide privacy signal.