mlsanityData to 7 Oct 2026

A Survey of Graph Unlearning

arXiv 2310.02164 ↗First posted 23 Aug 2023cs.LGcited by 12

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the textitright to be forgotten. It is evident that graph machine learning exhibits sensitivity to data privacy and adversarial attacks, necessitating the application of graph unlearning techniques to address these concerns effectively. In this comprehensive survey paper, we present the first systematic review of graph unlearning approaches, encompassing a diverse array of methodologies and offering a detailed taxonomy and up-to-date literature overview to facilitate the understanding of researchers new to this field. To ensure clarity, we provide lucid explanations of the fundamental concepts and evaluation measures used in graph unlearning, catering to a broader audience with varying levels of expertise. Delving into potential applications, we explore the versatility of graph unlearning across various domains, including but not limited to social networks, adversarial settings, recommender systems, and resource-constrained environments like the Internet of Things, illustrating its potential impact in safeguarding data privacy and enhancing AI systems' robustness. Finally, we shed light on promising research directions, encouraging further progress and innovation within the domain of graph unlearning. By laying a solid foundation and fostering continued progress, this survey seeks to inspire researchers to further advance the field of graph unlearning, thereby instilling confidence in the ethical growth of AI systems and reinforcing the responsible application of machine learning techniques in various domains.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 59 of its 134 references that are in the map. First posted on arXiv 23 Aug 2023.

Builds on

59 of 134 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Inductive Graph Unlearning6 Apr
  2. 2023GIF: A General Graph Unlearning Strategy via Influence Function6 Apr
  3. 2023Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection17 Feb
  4. 2022Unlearning Graph Classifiers with Limited Data Resources6 Nov
  5. 2022Certified Graph Unlearning18 Jun
  6. 2021Graph Unlearning27 Mar

Other references · 53

  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. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2023A Survey of Large Language Modelscited by 2,537
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  11. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  12. 2019Machine Unlearningcited by 1,020
38 more
  1. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  2. 2019Certified Data Removal from Machine Learning Modelscited by 512
  3. 2021Fast Model Editing at Scalecited by 491
  4. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  5. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  6. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  7. 2022A Survey of Machine Unlearningcited by 298
  8. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  9. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
  10. 2019A Survey on Graph Kernelscited by 148
  11. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  12. 2021Machine Unlearning via Algorithmic Stabilitycited by 128
  13. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
  14. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  15. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  16. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  17. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  18. 2020Rethinking pooling in graph neural networkscited by 73
  19. 2022Recommendation Unlearningcited by 71
  20. 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
  21. 2020Locally Private Graph Neural Networkscited by 64
  22. 2022Backdoor Defense with Machine Unlearningcited by 61
  23. 2022Theory of Graph Neural Networks: Representation and Learningcited by 60
  24. 2018NetLSD: Hearing the Shape of a Graphcited by 51
  25. 2022Are Attribute Inference Attacks Just Imputation?cited by 48
  26. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  27. 2018Diffusion Scattering Transforms on Graphscited by 43
  28. 2021Node-Level Differentially Private Graph Neural Networkscited by 43
  29. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  30. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 39
  31. 2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomicscited by 33
  32. 2021Releasing Graph Neural Networks with Differential Privacy Guaranteescited by 32
  33. 2021On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Modelscited by 30
  34. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  35. 2023Selective and Collaborative Influence Function for Efficient Recommendation Unlearningcited by 25
  36. 2023Recommendation Unlearning via Influence Functioncited by 21
  37. 2020Federated Dynamic GNN with Secure Aggregationcited by 15
  38. 2023Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendationscited by 12

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 3; 2026: 2.

12 papers.

  1. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  2. 2024Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barriercited by 13
  3. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  4. 2024Improving Graph Machine Learning Performance Through Feature Augmentation Based on Network Control Theorycited by 4
  5. 2024Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networkscited by 4
  6. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  7. 2024A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networkscited by 2
  8. 2026GDGU: A Gradient Difference-based Graph Unlearning Method for Cyberattack Localization in Electric Vehicle Charging Networkscited by 1
  9. 2024Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphscited by 0
  10. 2025Unlearning of Knowledge Graph Embedding via Preference Optimizationcited by 0
  11. 2025GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearningcited by 0
  12. 2026CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletioncited by 0