# Node-level Contrastive Unlearning on Graph Neural Networks

arXiv: https://arxiv.org/abs/2503.02959 · HTML: https://mlsanity.com/paper/2503.02959/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [Unlearning Graph Classifiers with Limited Data Resources](https://mlsanity.com/paper/2211.03216/) (2022)
- [Towards Effective and General Graph Unlearning via Mutual Evolution](https://mlsanity.com/paper/2401.11760/) (2024)
- [Graph Unlearning with Efficient Partial Retraining](https://mlsanity.com/paper/2403.07353/) (2024)
- [DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy](https://mlsanity.com/paper/2210.04442/) (2022)
- [On the Separability of Classes with the Cross-Entropy Loss Function](https://mlsanity.com/paper/1909.06930/) (2019)

## Built on by (most cited first, 1 of 1)

- [Unlearning Inversion Attacks for Graph Neural Networks](https://mlsanity.com/paper/2506.00808/) (2025)

## Abstract (arXiv)

Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph. Unlike machine unlearning for models trained on Euclidean-structured data, effectively unlearning a model trained on non-Euclidean-structured data, such as graphs, is challenging because graph entities exhibit mutual dependencies. Existing works utilize graph partitioning, influence function, or additional layers to achieve graph unlearning. However, none of them can achieve high scalability and effectiveness without additional constraints. In this paper, we achieve more effective graph unlearning by utilizing the embedding space. The primary training objective of a GNN is to generate proper embeddings for each node that encapsulates both structural information and node feature representations. Thus, directly optimizing the embedding space can effectively remove the target nodes' information from the model. Based on this intuition, we propose node-level contrastive unlearning (Node-CUL). It removes the influence of the target nodes (unlearning nodes) by contrasting the embeddings of remaining nodes and neighbors of unlearning nodes. Through iterative updates, the embeddings of unlearning nodes gradually become similar to those of unseen nodes, effectively removing the learned information without directly incorporating unseen data. In addition, we introduce a neighborhood reconstruction method that optimizes the embeddings of the neighbors in order to remove influence of unlearning nodes to maintain the utility of the GNN model. Experiments on various graph data and models show that our Node-CUL achieves the best unlearn efficacy and enhanced model utility with requiring comparable computing resources with existing frameworks.