# GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning

arXiv: https://arxiv.org/abs/2406.13499 · HTML: https://mlsanity.com/paper/2406.13499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [Rethinking Graph Neural Networks for Anomaly Detection](https://mlsanity.com/paper/2205.15508/) (2022)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Learning Graph Embedding with Adversarial Training Methods](https://mlsanity.com/paper/1901.01250/) (2019)
- [Transferring Robustness for Graph Neural Network Against Poisoning Attacks](https://mlsanity.com/paper/1908.07558/) (2019)
- [Certified Graph Unlearning](https://mlsanity.com/paper/2206.09140/) (2022)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [Adversarial Attack on Large Scale Graph](https://mlsanity.com/paper/2009.03488/) (2020)
- [How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?](https://mlsanity.com/paper/2306.06048/) (2023)
- [Inductive Graph Unlearning](https://mlsanity.com/paper/2304.03093/) (2023)
- [SAFE: Machine Unlearning With Shard Graphs](https://mlsanity.com/paper/2304.13169/) (2023)
- [Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection](https://mlsanity.com/paper/2302.08990/) (2023)
- [Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport](https://mlsanity.com/paper/2203.10453/) (2022)
- [Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns](https://mlsanity.com/paper/2312.13583/) (2023)
- [Spectral Adversarial Training for Robust Graph Neural Network](https://mlsanity.com/paper/2211.10896/) (2022)
- [GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections](https://mlsanity.com/paper/2210.12598/) (2022)

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

- [OpenGU: A Comprehensive Benchmark for Graph Unlearning](https://mlsanity.com/paper/2501.02728/) (2025)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel concept of model repair for GNNs. We propose a repair framework, Repairing Robustness of Graph Neural Networks via Machine Unlearning (GraphMU), which aims to fine-tune poisoned GNN to forget adversarial samples without the need for complete retraining. We also introduce a unlearning validation method to ensure that our approach effectively forget specified poisoned data. To evaluate the effectiveness of GraphMU, we explore three fine-tuned subgraph construction scenarios based on the available perturbation information: (i) Known Perturbation Ratios, (ii) Known Complete Knowledge of Perturbations, and (iii) Unknown any Knowledge of Perturbations. Our extensive experiments, conducted across four citation datasets and four adversarial attack scenarios, demonstrate that GraphMU can effectively restore the performance of poisoned GNN.