# Graph unlearning

Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/graph-unlearning/

## Key facts

- Graph unlearning: 33 papers on arXiv since 2021 (data through 7 Oct 2026).
- 21 of its 33 mapped papers (64%) cite “Graph Unlearning” (2021, arXiv 2103.14991).
- 19 of its 33 mapped papers (58%) cite “GIF: A General Graph Unlearning Strategy via Influence Function” (2023, arXiv 2304.02835).

## Most cited here

- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021), cited by 21 papers here
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023), cited by 19 papers here
- [Towards Effective and General Graph Unlearning via Mutual Evolution](https://mlsanity.com/paper/2401.11760/) (2024), cited by 16 papers here
- [Inductive Graph Unlearning](https://mlsanity.com/paper/2304.03093/) (2023), cited by 13 papers here
- [Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection](https://mlsanity.com/paper/2302.08990/) (2023), cited by 11 papers here
- [Certified Graph Unlearning](https://mlsanity.com/paper/2206.09140/) (2022), cited by 10 papers here
- [Unlearning Graph Classifiers with Limited Data Resources](https://mlsanity.com/paper/2211.03216/) (2022), cited by 8 papers here
- [Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning](https://mlsanity.com/paper/2409.16684/) (2024), cited by 6 papers here
- [Graph Unlearning with Efficient Partial Retraining](https://mlsanity.com/paper/2403.07353/) (2024), cited by 5 papers here
- [OpenGU: A Comprehensive Benchmark for Graph Unlearning](https://mlsanity.com/paper/2501.02728/) (2025), cited by 5 papers here