# Graph Unlearning: Efficient Node Removal in Graph Neural Networks

arXiv: https://arxiv.org/abs/2509.04785 · HTML: https://mlsanity.com/paper/2509.04785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Graph Neural Networks with convolutional ARMA filters](https://mlsanity.com/paper/1901.01343/) (2019)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [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)
- [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://mlsanity.com/paper/2203.00846/) (2022)
- [Coded Machine Unlearning](https://mlsanity.com/paper/2012.15721/) (2020)
- [A Hard Label Black-box Adversarial Attack Against Graph Neural Networks](https://mlsanity.com/paper/2108.09513/) (2021)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective](https://mlsanity.com/paper/2406.07314/) (2024)
- [Large Language Models for Link Stealing Attacks Against Graph Neural Networks](https://mlsanity.com/paper/2406.16963/) (2024)
- [Community-Centric Graph Unlearning](https://mlsanity.com/paper/2408.09705/) (2024)

## Abstract (arXiv)

With increasing concerns about privacy attacks and potential sensitive information leakage, researchers have actively explored methods to efficiently remove sensitive training data and reduce privacy risks in graph neural network (GNN) models. Node unlearning has emerged as a promising technique for protecting the privacy of sensitive nodes by efficiently removing specific training node information from GNN models. However, existing node unlearning methods either impose restrictions on the GNN structure or do not effectively utilize the graph topology for node unlearning. Some methods even compromise the graph's topology, making it challenging to achieve a satisfactory performance-complexity trade-off. To address these issues and achieve efficient unlearning for training node removal in GNNs, we propose three novel node unlearning methods: Class-based Label Replacement, Topology-guided Neighbor Mean Posterior Probability, and Class-consistent Neighbor Node Filtering. Among these methods, Topology-guided Neighbor Mean Posterior Probability and Class-consistent Neighbor Node Filtering effectively leverage the topological features of the graph, resulting in more effective node unlearning. To validate the superiority of our proposed methods in node unlearning, we conducted experiments on three benchmark datasets. The evaluation criteria included model utility, unlearning utility, and unlearning efficiency. The experimental results demonstrate the utility and efficiency of the proposed methods and illustrate their superiority compared to state-of-the-art node unlearning methods. Overall, the proposed methods efficiently remove sensitive training nodes and protect the privacy information of sensitive nodes in GNNs. The findings contribute to enhancing the privacy and security of GNN models and provide valuable insights into the field of node unlearning.