mlsanityData to 14 Oct 2026

Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach

arXiv 2508.02044 ↗First posted 4 Aug 2025cs.LG cs.AI cs.SIcited by 0

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achieves validity under partial edge unlearning, but faces challenges in dealing with more disturbing node unlearning. To avoid the overhead of retraining and realize the model utility of unlearning, we proposed a novel node unlearning method to reverse the process of aggregation in GNN by embedding reconstruction and to adopt Range-Null Space Decomposition for the nodes' interaction learning. Experimental results on multiple representative datasets demonstrate the SOTA performance of our proposed approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Graph unlearning, one of 12 directions in LLM safety and security. Builds on 23 of its 32 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

23 of 32 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearning6 Jan
  2. 2024Graph Unlearning with Efficient Partial Retraining12 Mar
  3. 2024Towards Effective and General Graph Unlearning via Mutual Evolution22 Jan
  4. 2023Inductive Graph Unlearning6 Apr
  5. 2023GIF: A General Graph Unlearning Strategy via Influence Function6 Apr
  6. 2023Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection17 Feb
  7. 2022Unlearning Graph Classifiers with Limited Data Resources6 Nov
  8. 2022Certified Graph Unlearning18 Jun
  9. 2021Graph Unlearning27 Mar

Other references · 14

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  3. 2019Machine Unlearningcited by 1,061
  4. 2019Certified Data Removal from Machine Learning Modelscited by 535
  5. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  6. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  7. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
  8. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  9. 2022Recommendation Unlearningcited by 80
  10. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
  11. 2024Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearningcited by 49
  12. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
2 more
  1. 2024IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networkscited by 22
  2. 2020Writing Polishment with Simile: Task, Dataset and A Neural Approachcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Node-level Contrastive Unlearning on Graph Neural Networks
  2. 2024Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning
  3. 2024Community-Centric Graph Unlearning
  4. 2024Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
  5. 2025Forget and Explain: Transparent Verification of GNN Unlearning
  6. 2025Unlearning Inversion Attacks for Graph Neural Networks
  7. 2024TCGU: Data-centric Graph Unlearning based on Transferable Condensation
  8. 2025Graph Unlearning Meets Influence-aware Negative Preference Optimization