# TCGU: Data-centric Graph Unlearning based on Transferable Condensation

arXiv: https://arxiv.org/abs/2410.06480 · HTML: https://mlsanity.com/paper/2410.06480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Graph unlearning, one of 12 directions in LLM safety and security.
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [Improved Distribution Matching for Dataset Condensation](https://mlsanity.com/paper/2307.09742/) (2023)
- [Condensing Graphs via One-Step Gradient Matching](https://mlsanity.com/paper/2206.07746/) (2022)
- [Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data](https://mlsanity.com/paper/2306.02664/) (2023)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification](https://mlsanity.com/paper/1906.02319/) (2019)
- [CaT: Balanced Continual Graph Learning with Graph Condensation](https://mlsanity.com/paper/2309.09455/) (2023)
- [Algorithms that Approximate Data Removal: New Results and Limitations](https://mlsanity.com/paper/2209.12269/) (2022)
- [Fast Graph Condensation with Structure-based Neural Tangent Kernel](https://mlsanity.com/paper/2310.11046/) (2023)
- [Towards Effective and General Graph Unlearning via Mutual Evolution](https://mlsanity.com/paper/2401.11760/) (2024)
- [FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks](https://mlsanity.com/paper/2309.09517/) (2023)

## Abstract (arXiv)

With growing demands for data privacy and model robustness, graph unlearning (GU), which erases the influence of specific data on trained GNN models, has gained significant attention. However, existing exact unlearning methods suffer from either low efficiency or poor model performance. While being more utility-preserving and efficient, current approximate unlearning methods are not applicable in the zero-glance privacy setting, where the deleted samples cannot be accessed during unlearning due to immediate deletion requested by regulations. Besides, these approximate methods, which try to directly perturb model parameters still involve high privacy concerns in practice. To fill the gap, we propose Transferable Condensation Graph Unlearning (TCGU), a data-centric solution to zero-glance graph unlearning. Specifically, we first design a two-level alignment strategy to pre-condense the original graph into a small yet utility-preserving dataset. Upon receiving an unlearning request, we fine-tune the pre-condensed data with a low-rank plugin, to directly align its distribution with the remaining graph, thus efficiently revoking the information of deleted data without accessing them. A novel similarity distribution matching approach and a discrimination regularizer are proposed to effectively transfer condensed data and preserve its utility in GNN training, respectively. Finally, we retrain the GNN on the transferred condensed data. Extensive experiments on 6 benchmark datasets demonstrate that TCGU can achieve superior performance in terms of model utility, unlearning efficiency, and unlearning efficacy than existing GU methods.