mlsanityData to 7 Oct 2026

Graph Unlearning with Efficient Partial Retraining

arXiv 2403.07353 ↗First posted 12 Mar 2024cs.LG cs.CRcited by 20

On the map: LLM safety and security → Graph unlearning

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach.

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 24 of its 32 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

24 of 32 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023GIF: A General Graph Unlearning Strategy via Influence Function6 Apr
  2. 2021Graph Unlearning27 Mar

Other references · 22

  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. 2019Machine Unlearningcited by 1,020
  5. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  7. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  8. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  9. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  10. 2019Certified Data Removal from Machine Learning Modelscited by 512
  11. 2021Machine Unlearning of Features and Labelscited by 223
  12. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
10 more
  1. 2020Machine Unlearning for Random Forestscited by 125
  2. 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
  3. 2022Recommendation Unlearningcited by 71
  4. 2021Graph Trend Filtering Networks for Recommendationscited by 53
  5. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  6. 2024Linear-Time Graph Neural Networks for Scalable Recommendationscited by 31
  7. 2022Disentangled Contrastive Learning for Social Recommendationcited by 27
  8. 2022Knowledge-enhanced Black-box Attacks for Recommendationscited by 25
  9. 2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
  10. 2021Large-Scale Network Embedding in Apache Sparkcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 11; 2026: 5.

20 papers.

Sort:

By area:

  1. 2024Graph Machine Learning in the Era of Large Language Models (LLMs)cited by 33
  2. 2024Score-based Generative Diffusion Models for Social Recommendationscited by 23
  3. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
  4. 2025Targeted Forgetting of Image Subgroups in CLIP Modelscited by 6
  5. 2024Backdoor Graph Condensationcited by 5
  6. 2024SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Modelscited by 5
  7. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  8. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generationcited by 4
  9. 2025Neural Algorithmic Reasoning for Hypergraphs with Looped Transformerscited by 3
  10. 2026Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systemscited by 3
  11. 2025Toward Scalable Graph Unlearning: A Node Influence Maximization based Approachcited by 2
  12. 2026Re-understanding Graph Unlearning through Memorizationcited by 2
8 more
  1. 2025Node-level Contrastive Unlearning on Graph Neural Networkscited by 1
  2. 2025Enhance GNNs with Reliable Confidence Estimation via Adversarial Calibration Learningcited by 1
  3. 2026Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networkscited by 1
  4. 2026Rethinking Demonstration Unlearning in Imitation Learning for Roboticscited by 1
  5. 2025Unlearning Algorithmic Biases over Graphscited by 0
  6. 2025Unlearning of Knowledge Graph Embedding via Preference Optimizationcited by 0
  7. 2025Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approachcited by 0
  8. 2026The Confidence Trap: Calibration Attacks for Graph Neural Networkscited by 0