mlsanityData to 7 Oct 2026

Graph Unlearning

arXiv 2103.14991 ↗First posted 27 Mar 2021cs.LG cs.AI cs.CRcited by 129

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legitimate, retraining the ML model from scratch incurs a high computational overhead. To address this issue, a number of approximate algorithms have been proposed in the domain of image and text data, among which SISA is the state-of-the-art solution. It randomly partitions the training set into multiple shards and trains a constituent model for each shard. However, directly applying SISA to the graph data can severely damage the graph structural information, and thereby the resulting ML model utility. In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data. Its contributions include two novel graph partition algorithms and a learning-based aggregation method. We conduct extensive experiments on five real-world graph datasets to illustrate the unlearning efficiency and model utility of GraphEraser. It achieves 2.06× (small dataset) to 35.94× (large dataset) unlearning time improvement. On the other hand, GraphEraser achieves up to 62.5% higher F1 score and our proposed learning-based aggregation method achieves up to 112% higher F1 score.footnoteOur code is available at urlhttps://github.com/MinChen00/Graph-Unlearning.

Key facts. Cited by 129 papers in the map (data through 7 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 58 of its 103 references that are in the map. First posted on arXiv 27 Mar 2021.

Builds on

58 of 103 references.

References · 58

  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. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  10. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  11. 2019Machine Unlearningcited by 1,020
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
38 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  3. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  4. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  5. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  7. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  8. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  9. 2019Certified Data Removal from Machine Learning Modelscited by 512
  10. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  11. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  12. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  13. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  14. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  15. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  16. 2015Diffusion-Convolutional Neural Networkscited by 268
  17. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  18. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  19. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  20. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  21. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  22. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  23. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 158
  24. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 147
  25. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  26. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  27. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  28. 2020Machine Unlearning for Random Forestscited by 125
  29. 2020Stealing Links from Graph Neural Networkscited by 114
  30. 2020Unifying Graph Convolutional Neural Networks and Label Propagationcited by 98
  31. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89
  32. 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
  33. 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
  34. 2019Overlearning Reveals Sensitive Attributescited by 74
  35. 2020Locally Private Graph Neural Networkscited by 64
  36. 2019DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classificationcited by 59
  37. 2020Towards Probabilistic Verification of Machine Unlearningcited by 46
  38. 2020Adversarial Privacy Preserving Graph Embedding against Inference Attackcited by 21

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 12; 2023: 21; 2024: 49; 2025: 29; 2026: 17.

129 papers.

Sort:

By area:

  1. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
  2. 2022A Survey of Machine Unlearningcited by 298
  3. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  4. 2023Model Sparsity Can Simplify Machine Unlearningcited by 206
  5. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  6. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 109
  7. 2023Machine Unlearning: Solutions and Challengescited by 85
  8. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  9. 2022Backdoor Defense with Machine Unlearningcited by 61
  10. 2023GIF: A General Graph Unlearning Strategy via Influence Functioncited by 59
  11. 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 58
  12. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
38 more
  1. 2024AnyGraph: Graph Foundation Model in the Wildcited by 51
  2. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 50
  3. 2022Certified Graph Unlearningcited by 46
  4. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  5. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  6. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  7. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  8. 2022Deep Regression Unlearningcited by 32
  9. 2022Unlearning Graph Classifiers with Limited Data Resourcescited by 31
  10. 2023Inductive Graph Unlearningcited by 30
  11. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  12. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  13. 2024Towards Certified Unlearning for Deep Neural Networkscited by 28
  14. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendationcited by 27
  15. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  16. 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Modelscited by 25
  17. 2022Verifiable and Provably Secure Machine Unlearningcited by 24
  18. 2025BLUR: A Bi-Level Optimization Approach for LLM Unlearningcited by 23
  19. 2024Editable Concept Bottleneck Modelscited by 22
  20. 2024IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networkscited by 22
  21. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 22
  22. 2022Machine Unlearning of Federated Clusterscited by 21
  23. 2023Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projectioncited by 20
  24. 2023MultiDelete for Multimodal Machine Unlearningcited by 20
  25. 2024Graph Unlearning with Efficient Partial Retrainingcited by 20
  26. 2024Verification of Machine Unlearning is Fragilecited by 20
  27. 2024When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?cited by 20
  28. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
  29. 2023To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methodscited by 18
  30. 2023Machine Unlearning: A Surveycited by 18
  31. 2024MUNBa: Machine Unlearning via Nash Bargainingcited by 17
  32. 2025LLM Unlearning with LLM Beliefscited by 17
  33. 2024Towards Efficient and Effective Unlearning of Large Language Models for Recommendationcited by 16
  34. 2024Adversarial Machine Unlearningcited by 16
  35. 2024MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearningcited by 16
  36. 2023ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approachcited by 15
  37. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  38. 2024Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policiescited by 15

50 most cited of 129 All 129 (JSON)