mlsanityData to 7 Oct 2026

Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection

arXiv 2302.08990 ↗First posted 17 Feb 2023cs.LG cs.AIcited by 20

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

As privacy protection receives much attention, unlearning the effect of a specific node from a pre-trained graph learning model has become equally important. However, due to the node dependency in the graph-structured data, representation unlearning in Graph Neural Networks (GNNs) is challenging and less well explored. In this paper, we fill in this gap by first studying the unlearning problem in linear-GNNs, and then introducing its extension to non-linear structures. Given a set of nodes to unlearn, we propose PROJECTOR that unlearns by projecting the weight parameters of the pre-trained model onto a subspace that is irrelevant to features of the nodes to be forgotten. PROJECTOR could overcome the challenges caused by node dependency and enjoys a perfect data removal, i.e., the unlearned model parameters do not contain any information about the unlearned node features which is guaranteed by algorithmic construction. Empirical results on real-world datasets illustrate the effectiveness and efficiency of PROJECTOR.

Key facts. Cited by 20 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 56 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

37 of 56 references.

Closest ancestors · 2

Same direction, newest first

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

Other references · 35

  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. 2021Convex optimizationcited by 2,479
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2019Machine Unlearningcited by 1,020
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  9. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  10. 2019Certified Data Removal from Machine Learning Modelscited by 512
  11. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  12. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
23 more
  1. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 342
  2. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  3. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  4. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  5. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
  6. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  7. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  8. 2021Machine Unlearning via Algorithmic Stabilitycited by 128
  9. 2020Machine Unlearning for Random Forestscited by 125
  10. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  11. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  12. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  13. 2022Recommendation Unlearningcited by 71
  14. 2021On Provable Benefits of Depth in Training Graph Convolutional Networkscited by 58
  15. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 56
  16. 2021Bag of Tricks for Node Classification with Graph Neural Networkscited by 40
  17. 2020Coded Machine Unlearningcited by 35
  18. 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
  19. 2021Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networkscited by 24
  20. 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 20
  21. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
  22. 2020PrIU: A Provenance-Based Approach for Incrementally Updating Regression Modelscited by 16
  23. 2020Deep Graph Neural Networks with Shallow Subgraph Samplerscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 4; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  2. 2024Towards Effective and General Graph Unlearning via Mutual Evolutioncited by 29
  3. 2023MultiDelete for Multimodal Machine Unlearningcited by 20
  4. 2024MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearningcited by 16
  5. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  6. 2023Subspace based Federated Unlearningcited by 13
  7. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillationcited by 13
  8. 2023DUCK: Distance-based Unlearning via Centroid Kinematicscited by 13
  9. 2024Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barriercited by 13
  10. 2023A Survey of Graph Unlearningcited by 12
  11. 2024Unlink to Unlearn: Simplifying Edge Unlearning in GNNscited by 11
  12. 2024Brain-inspired Artificial Intelligence: A Comprehensive Reviewcited by 8
8 more
  1. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
  2. 2024"Forgetting" in Machine Learning and Beyond: A Surveycited by 2
  3. 2025Toward Scalable Graph Unlearning: A Node Influence Maximization based Approachcited by 2
  4. 2024GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearningcited by 1
  5. 2026Spatial Entropy based Partitioning for Spatiotemporal Graph Unlearningcited by 1
  6. 2025Unlearning Algorithmic Biases over Graphscited by 0
  7. 2025Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approachcited by 0
  8. 2026CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletioncited by 0