# Graph Unlearning with Efficient Partial Retraining

arXiv: https://arxiv.org/abs/2403.07353 · HTML: https://mlsanity.com/paper/2403.07353/

## Key facts

- Cited by 20 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Graph unlearning](https://mlsanity.com/safety/graph-unlearning/)

## Builds on (most cited first, 24 of 24)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [Graph Trend Filtering Networks for Recommendations](https://mlsanity.com/paper/2108.05552/) (2021)
- [Fast Graph Condensation with Structure-based Neural Tangent Kernel](https://mlsanity.com/paper/2310.11046/) (2023)
- [Linear-Time Graph Neural Networks for Scalable Recommendations](https://mlsanity.com/paper/2402.13973/) (2024)
- [Disentangled Contrastive Learning for Social Recommendation](https://mlsanity.com/paper/2208.08723/) (2022)
- [Knowledge-enhanced Black-box Attacks for Recommendations](https://mlsanity.com/paper/2207.10307/) (2022)
- [Jointly Attacking Graph Neural Network and its Explanations](https://mlsanity.com/paper/2108.03388/) (2021)
- [Large-Scale Network Embedding in Apache Spark](https://mlsanity.com/paper/2106.10620/) (2021)

## Built on by (most cited first, 20 of 20)

- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Score-based Generative Diffusion Models for Social Recommendations](https://mlsanity.com/paper/2412.15579/) (2024)
- [OpenGU: A Comprehensive Benchmark for Graph Unlearning](https://mlsanity.com/paper/2501.02728/) (2025)
- [Targeted Forgetting of Image Subgroups in CLIP Models](https://mlsanity.com/paper/2506.03117/) (2025)
- [Backdoor Graph Condensation](https://mlsanity.com/paper/2407.11025/) (2024)
- [SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models](https://mlsanity.com/paper/2409.00055/) (2024)
- [Exposing Privacy Risks in Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.17222/) (2025)
- [Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers](https://mlsanity.com/paper/2501.10688/) (2025)
- [Unlearning Inversion Attacks for Graph Neural Networks](https://mlsanity.com/paper/2506.00808/) (2025)
- [Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems](https://mlsanity.com/paper/2601.14662/) (2026)
- [Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach](https://mlsanity.com/paper/2501.11823/) (2025)
- [Re-understanding Graph Unlearning through Memorization](https://mlsanity.com/paper/2601.14694/) (2026)
- [Node-level Contrastive Unlearning on Graph Neural Networks](https://mlsanity.com/paper/2503.02959/) (2025)
- [Enhance GNNs with Reliable Confidence Estimation via Adversarial Calibration Learning](https://mlsanity.com/paper/2503.18235/) (2025)
- [Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2603.18570/) (2026)
- [Rethinking Demonstration Unlearning in Imitation Learning for Robotics](https://mlsanity.com/paper/2608.20784/) (2026)
- [Unlearning Algorithmic Biases over Graphs](https://mlsanity.com/paper/2505.14945/) (2025)
- [Unlearning of Knowledge Graph Embedding via Preference Optimization](https://mlsanity.com/paper/2507.20566/) (2025)
- [Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach](https://mlsanity.com/paper/2508.02044/) (2025)
- [The Confidence Trap: Calibration Attacks for Graph Neural Networks](https://mlsanity.com/paper/2606.08467/) (2026)

## 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.