mlsanityData to 7 Oct 2026

OpenGU: A Comprehensive Benchmark for Graph Unlearning

arXiv 2501.02728 ↗First posted 6 Jan 2025cs.LG cs.AIcited by 8

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

Graph Machine Learning is essential for understanding and analyzing relational data. However, privacy-sensitive applications demand the ability to efficiently remove sensitive information from trained graph neural networks (GNNs), avoiding the unnecessary time and space overhead caused by retraining models from scratch. To address this issue, Graph Unlearning (GU) has emerged as a critical solution, with the potential to support dynamic graph updates in data management systems and enable scalable unlearning in distributed data systems while ensuring privacy compliance. Unlike machine unlearning in computer vision or other fields, GU faces unique difficulties due to the non-Euclidean nature of graph data and the recursive message-passing mechanism of GNNs. Additionally, the diversity of downstream tasks and the complexity of unlearning requests further amplify these challenges. Despite the proliferation of diverse GU strategies, the absence of a benchmark providing fair comparisons for GU, and the limited flexibility in combining downstream tasks and unlearning requests, have yielded inconsistencies in evaluations, hindering the development of this domain. To fill this gap, we present OpenGU, the first GU benchmark, where 16 SOTA GU algorithms and 37 multi-domain datasets are integrated, enabling various downstream tasks with 13 GNN backbones when responding to flexible unlearning requests. Based on this unified benchmark framework, we are able to provide a comprehensive and fair evaluation for GU. Through extensive experimentation, we have drawn 8 crucial conclusions about existing GU methods, while also gaining valuable insights into their limitations, shedding light on potential avenues for future research.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 60 of its 105 references that are in the map. First posted on arXiv 6 Jan 2025.

Builds on

60 of 105 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier17 Aug
  2. 2024Graph Unlearning with Efficient Partial Retraining12 Mar
  3. 2024Towards Effective and General Graph Unlearning via Mutual Evolution22 Jan
  4. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation28 Sep
  5. 2023Inductive Graph Unlearning6 Apr
  6. 2023GIF: A General Graph Unlearning Strategy via Influence Function6 Apr
  7. 2023Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection17 Feb
  8. 2022Unlearning Graph Classifiers with Limited Data Resources6 Nov
  9. 2022Certified Graph Unlearning18 Jun
  10. 2021Graph Unlearning27 Mar

Other references · 50

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  10. 2019Machine Unlearningcited by 1,020
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  12. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
38 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2020Simple and Deep Graph Convolutional Networkscited by 857
  3. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  4. 2021How Attentive are Graph Attention Networks?cited by 818
  5. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  6. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  7. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  8. 2019Graph Transformer Networkscited by 520
  9. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  11. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  12. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  13. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  14. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 211
  15. 2021Fast Yet Effective Machine Unlearningcited by 209
  16. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  17. 2021Graph Neural Networks in Network Neurosciencecited by 91
  18. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  19. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  20. 2023LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendationcited by 72
  21. 2020Supervised Learning on Relational Databases with Graph Neural Networkscited by 48
  22. 2020Graph Neural Networks: Taxonomy, Advances and Trendscited by 48
  23. 2018Deep Reasoning with Knowledge Graph for Social Relationship Understandingcited by 44
  24. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  25. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  26. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  27. 2024From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attackscited by 29
  28. 2024Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningcited by 25
  29. 2024IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networkscited by 22
  30. 2023Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearningcited by 21
  31. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  32. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  33. 2022Label-Only Membership Inference Attack against Node-Level Graph Neural Networkscited by 18
  34. 2022Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representationscited by 16
  35. 2017An introduction to Graph Data Managementcited by 11
  36. 2024Unlink to Unlearn: Simplifying Edge Unlearning in GNNscited by 11
  37. 2024Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgettingcited by 7
  38. 2024GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  2. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generationcited by 4
  3. 2025Adaptive Graph Unlearningcited by 2
  4. 2026Re-understanding Graph Unlearning through Memorizationcited by 2
  5. 2026GDGU: A Gradient Difference-based Graph Unlearning Method for Cyberattack Localization in Electric Vehicle Charging Networkscited by 1
  6. 2025Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approachcited by 0
  7. 2026FairGU: Fairness-aware Graph Unlearning in Social Networkscited by 0
  8. 2026CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletioncited by 0