Summary of Idea: a Flexible Framework Of Certified Unlearning For Graph Neural Networks, by Yushun Dong et al.
IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
by Yushun Dong, Binchi Zhang, Zhenyu Lei, Na Zou, Jundong Li
First submitted to arxiv on: 28 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a framework called IDEA for achieving flexible and certified unlearning for Graph Neural Networks (GNNs). Certified unlearning is a technique that aims to remove personal information from trained GNNs, providing a theoretical guarantee of effectiveness. Current methods are limited in their flexibility, as they’re tailored for specific GNN designs or training objectives. The authors instantiate four types of unlearning requests on graphs and propose an approximation approach to handle these requests over diverse GNNs. They provide theoretical guarantees for the proposed approach’s effectiveness. Experiments on real-world datasets demonstrate IDEA’s superiority. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary IDEA is a new way to remove personal information from trained Graph Neural Networks (GNNs). This helps keep private data safe when the trained models are shared. Right now, there aren’t many ways to do this that also work well and can be used with different GNN designs or training goals. The authors created a flexible method that can handle different types of requests for removing information from graphs and GNNs. They tested it on real-world data and showed that it works better than other methods. |
Keywords
* Artificial intelligence * Gnn
