# Unlink to Unlearn: Simplifying Edge Unlearning in GNNs

arXiv: https://arxiv.org/abs/2402.10695 · HTML: https://mlsanity.com/paper/2402.10695/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [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)
- [Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection](https://mlsanity.com/paper/2302.08990/) (2023)

## Built on by (most cited first, 11 of 11)

- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [On Effects of Steering Latent Representation for Large Language Model Unlearning](https://mlsanity.com/paper/2408.06223/) (2024)
- [OpenGU: A Comprehensive Benchmark for Graph Unlearning](https://mlsanity.com/paper/2501.02728/) (2025)
- [FROG: Fair Removal on Graphs](https://mlsanity.com/paper/2503.18197/) (2025)
- [Graph Unlearning Meets Influence-aware Negative Preference Optimization](https://mlsanity.com/paper/2510.19479/) (2025)
- [A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks](https://mlsanity.com/paper/2412.00789/) (2024)
- [Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach](https://mlsanity.com/paper/2501.11823/) (2025)
- [Adaptive Graph Unlearning](https://mlsanity.com/paper/2505.12614/) (2025)
- [Re-understanding Graph Unlearning through Memorization](https://mlsanity.com/paper/2601.14694/) (2026)
- [Forget and Explain: Transparent Verification of GNN Unlearning](https://mlsanity.com/paper/2512.07450/) (2025)
- [CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion](https://mlsanity.com/paper/2609.08244/) (2026)

## Abstract (arXiv)

As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia. This concept is pivotal in enforcing the textitright to be forgotten, which entails the selective removal of specific data from trained GNNs upon user request. Our research focuses on edge unlearning, a process of particular relevance to real-world applications. Current state-of-the-art approaches like GNNDelete can eliminate the influence of specific edges yet suffer from textitover-forgetting, which means the unlearning process inadvertently removes excessive information beyond needed, leading to a significant performance decline for remaining edges. Our analysis identifies the loss functions of GNNDelete as the primary source of over-forgetting and also suggests that loss functions may be redundant for effective edge unlearning. Building on these insights, we simplify GNNDelete to develop Unlink to Unlearn (UtU), a novel method that facilitates unlearning exclusively through unlinking the forget edges from graph structure. Our extensive experiments demonstrate that UtU delivers privacy protection on par with that of a retrained model while preserving high accuracy in downstream tasks, by upholding over 97.3% of the retrained model's privacy protection capabilities and 99.8% of its link prediction accuracy. Meanwhile, UtU requires only constant computational demands, underscoring its advantage as a highly lightweight and practical edge unlearning solution.