mlsanityData to 7 Oct 2026

Inductive Graph Unlearning

arXiv 2304.03093 ↗First posted 6 Apr 2023cs.LG cs.CR cs.SIcited by 30

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

As a way to implement the "right to be forgotten" in machine learning, textitmachine unlearning aims to completely remove the contributions and information of the samples to be deleted from a trained model without affecting the contributions of other samples. Recently, many frameworks for machine unlearning have been proposed, and most of them focus on image and text data. To extend machine unlearning to graph data, textitGraphEraser has been proposed. However, a critical issue is that textitGraphEraser is specifically designed for the transductive graph setting, where the graph is static and attributes and edges of test nodes are visible during training. It is unsuitable for the inductive setting, where the graph could be dynamic and the test graph information is invisible in advance. Such inductive capability is essential for production machine learning systems with evolving graphs like social media and transaction networks. To fill this gap, we propose the underlinebf Gunderlinebf Uided underlinebf Inunderlinebf Ductivunderlinebf E Graph Unlearning framework (GUIDE). GUIDE consists of three components: guided graph partitioning with fairness and balance, efficient subgraph repair, and similarity-based aggregation. Empirically, we evaluate our method on several inductive benchmarks and evolving transaction graphs. Generally speaking, GUIDE can be efficiently implemented on the inductive graph learning tasks for its low graph partition cost, no matter on computation or structure information. The code will be available here: https://github.com/Happy2Git/GUIDE.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 54 of its 75 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

54 of 75 references.

Closest ancestors · 1

Same direction, newest first

  1. 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. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  9. 2019Machine Unlearningcited by 1,020
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  11. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
38 more
  1. 2021How Attentive are Graph Attention Networks?cited by 818
  2. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  3. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  4. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  5. 2019Certified Data Removal from Machine Learning Modelscited by 512
  6. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  8. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  9. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  10. 2020Amnesiac Machine Learningcited by 305
  11. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 274
  12. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  13. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  14. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  15. 2018Fair Clustering Through Fairletscited by 176
  16. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  17. 2021Adaptive Machine Unlearningcited by 164
  18. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 158
  19. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  20. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  21. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  22. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  23. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  24. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  25. 2021Machine Unlearning via Algorithmic Stabilitycited by 128
  26. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  27. 2019On the Apparent Conflict Between Individual and Group Fairnesscited by 126
  28. 2020Machine Unlearning for Random Forestscited by 125
  29. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  30. 2021FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendationcited by 97
  31. 2019Peer-to-peer Federated Learning on Graphscited by 85
  32. 2019Scalable Fair Clusteringcited by 78
  33. 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
  34. 2022Recommendation Unlearningcited by 71
  35. 2020Individual Fairness for k-Clusteringcited by 56
  36. 2018GraKeL: A Graph Kernel Library in Pythoncited by 54
  37. 2020Fair clustering via equitable group representationscited by 43
  38. 2021FedGraph: Federated Graph Learning with Intelligent Samplingcited by 34

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 9; 2025: 10; 2026: 5.

30 papers.

Sort:

By area:

  1. 2023Machine Unlearning: Solutions and Challengescited by 85
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  3. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  4. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  5. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparitiescited by 25
  6. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillationcited by 13
  7. 2024Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barriercited by 13
  8. 2023A Survey of Graph Unlearningcited by 12
  9. 2025Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completenesscited by 11
  10. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
  11. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  12. 2024Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgottencited by 3
18 more
  1. 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approachcited by 3
  2. 2025Enabling Group Fairness in Graph Unlearning via Bi-level Debiasingcited by 3
  3. 2024Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearningcited by 2
  4. 2025Adaptive Graph Unlearningcited by 2
  5. 2026Re-understanding Graph Unlearning through Memorizationcited by 2
  6. 2024GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearningcited by 1
  7. 2025Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibriumcited by 1
  8. 2026Spatial Entropy based Partitioning for Spatiotemporal Graph Unlearningcited by 1
  9. 2024Review of Digital Asset Development with Graph Neural Network Unlearningcited by 0
  10. 2024Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakagecited by 0
  11. 2024Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphscited by 0
  12. 2025Unlearning Algorithmic Biases over Graphscited by 0
  13. 2025Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignmentcited by 0
  14. 2025Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approachcited by 0
  15. 2025GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearningcited by 0
  16. 2026Stable Multimodal Graph Unlearning via Feature-Dimension Aware Quantile Selectioncited by 0
  17. 2026FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filterscited by 0
  18. 2026CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletioncited by 0