mlsanityData to 7 Oct 2026

Unlearning Graph Classifiers with Limited Data Resources

arXiv 2211.03216 ↗First posted 6 Nov 2022cs.LG cs.CRcited by 31

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

As the demand for user privacy grows, controlled data removal (machine unlearning) is becoming an important feature of machine learning models for data-sensitive Web applications such as social networks and recommender systems. Nevertheless, at this point it is still largely unknown how to perform efficient machine unlearning of graph neural networks (GNNs); this is especially the case when the number of training samples is small, in which case unlearning can seriously compromise the performance of the model. To address this issue, we initiate the study of unlearning the Graph Scattering Transform (GST), a mathematical framework that is efficient, provably stable under feature or graph topology perturbations, and offers graph classification performance comparable to that of GNNs. Our main contribution is the first known nonlinear approximate graph unlearning method based on GSTs. Our second contribution is a theoretical analysis of the computational complexity of the proposed unlearning mechanism, which is hard to replicate for deep neural networks. Our third contribution are extensive simulation results which show that, compared to complete retraining of GNNs after each removal request, the new GST-based approach offers, on average, a 10.38x speed-up and leads to a 2.6% increase in test accuracy during unlearning of 90 out of 100 training graphs from the IMDB dataset (10% training ratio). Our implementation is available online at https://doi.org/10.5281/zenodo.7613150.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 37 of its 62 references that are in the map. First posted on arXiv 6 Nov 2022.

Builds on

37 of 62 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Certified Graph Unlearning18 Jun
  2. 2021Graph Unlearning27 Mar

Other references · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2019Machine Unlearningcited by 1,020
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  10. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  11. 2019Graph Neural Networks for Social Recommendationcited by 711
  12. 2020Benchmarking Graph Neural Networkscited by 672
23 more
  1. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  2. 2019Certified Data Removal from Machine Learning Modelscited by 512
  3. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  4. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  5. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  6. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  7. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  8. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  9. 2020Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networkscited by 57
  10. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  11. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 52
  12. 2014PageRank beyond the Webcited by 51
  13. 2018Geometric Scattering for Graph Data Analysiscited by 49
  14. 2021Knowledge-aware Coupled Graph Neural Network for Social Recommendationcited by 49
  15. 2018Graph Convolutional Neural Networks via Scatteringcited by 46
  16. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  17. 2018Diffusion Scattering Transforms on Graphscited by 43
  18. 2021Node-Level Differentially Private Graph Neural Networkscited by 43
  19. 2019Graph Neural Network for Interpreting Task-fMRI Biomarkerscited by 40
  20. 2019Stability of Graph Scattering Transformscited by 34
  21. 2022Machine Unlearning of Federated Clusterscited by 21
  22. 2020Spatio-Temporal Graph Scattering Transformcited by 19
  23. 2013Spectrum-Adapted Tight Graph Wavelet and Vertex-Frequency Framescited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 11; 2025: 9; 2026: 3.

31 papers.

Sort:

By area:

  1. 2023Machine Unlearning: Solutions and Challengescited by 85
  2. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  3. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  4. 2024Towards Certified Unlearning for Deep Neural Networkscited by 28
  5. 2024IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networkscited by 22
  6. 2023Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearningcited by 21
  7. 2024Verification of Machine Unlearning is Fragilecited by 20
  8. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  9. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillationcited by 13
  10. 2023DUCK: Distance-based Unlearning via Centroid Kinematicscited by 13
  11. 2024Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barriercited by 13
  12. 2023Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protectioncited by 12
19 more
  1. 2023A Survey of Graph Unlearningcited by 12
  2. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  3. 2024Machine Unlearning for Recommendation Systems: An Insightcited by 9
  4. 2023GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networkscited by 8
  5. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
  6. 2025UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearningcited by 7
  7. 2025TAPE: Tailored Posterior Difference for Auditing of Machine Unlearningcited by 6
  8. 2026SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generationcited by 6
  9. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  10. 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approachcited by 3
  11. 2025Toward Scalable Graph Unlearning: A Node Influence Maximization based Approachcited by 2
  12. 2025Node-level Contrastive Unlearning on Graph Neural Networkscited by 1
  13. 2026Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networkscited by 1
  14. 2026GDGU: A Gradient Difference-based Graph Unlearning Method for Cyberattack Localization in Electric Vehicle Charging Networkscited by 1
  15. 2024Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attackscited by 0
  16. 2024Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphscited by 0
  17. 2025Unlearning Algorithmic Biases over Graphscited by 0
  18. 2025Unlearning of Knowledge Graph Embedding via Preference Optimizationcited by 0
  19. 2025Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approachcited by 0