Summary of Community-centric Graph Unlearning, by Yi Li et al.
Community-Centric Graph Unlearning
by Yi Li, Shichao Zhang, Guixian Zhang, Debo Cheng
First submitted to arxiv on: 19 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Social and Information Networks (cs.SI)
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 This paper proposes a novel approach to graph unlearning called Community-centric Graph Eraser (CGE), which addresses limitations in existing frameworks. The authors describe how current deterministic methods suffer from a lack of structural information between subgraph neighborhoods, leading to redundant calculations. CGE maps community subgraphs to nodes, allowing for node-level unlearning operations within a reduced mapped graph. This results in an exponential reduction of training data and unlearning parameters. The paper evaluates CGE on five real-world datasets and three GNN backbones, demonstrating high performance and efficiency. The proposed method has potential applications in the field of graph unlearning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us figure out how to remove unwanted information from artificial intelligence models that deal with graphs. Graphs are like maps that show connections between things. When we want to remove some of this information, it’s called “unlearning.” The problem is that current ways of doing this can be slow and wasteful. The authors came up with a new idea called Community-centric Graph Eraser (CGE) that makes the process faster and more efficient. They tested CGE on lots of different datasets and showed that it works well. This could help us make AI models that are better at keeping our information private. |
Keywords
* Artificial intelligence * Gnn
