GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914841560612864 |
|---|---|
| author | Wu, Tao Cao, Xinwen Wang, Chao Qiao, Shaojie Xian, Xingping Yuan, Lin Cui, Canyixing Liu, Yanbing |
| author_facet | Wu, Tao Cao, Xinwen Wang, Chao Qiao, Shaojie Xian, Xingping Yuan, Lin Cui, Canyixing Liu, Yanbing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13499 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning Wu, Tao Cao, Xinwen Wang, Chao Qiao, Shaojie Xian, Xingping Yuan, Lin Cui, Canyixing Liu, Yanbing Social and Information Networks Machine Learning 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. |
| title | GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning |
| topic | Social and Information Networks Machine Learning |
| url | https://arxiv.org/abs/2406.13499 |