Summary of Generating In-distribution Proxy Graphs For Explaining Graph Neural Networks, by Zhuomin Chen et al.
Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
by Zhuomin Chen, Jiaxing Zhang, Jingchao Ni, Xiaoting Li, Yuchen Bian, Md Mezbahul Islam, Ananda Mohan Mondal, Hua Wei, Dongsheng Luo
First submitted to arxiv on: 3 Feb 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 This paper proposes a novel method to improve the explainability of Graph Neural Networks (GNNs) in high-stakes applications. The approach generates proxy graphs that are closer to the training data distribution, enabling more accurate predictions and explanations of GNN outputs. By employing graph generators and a new information-theoretic training objective, the proposed method produces proxy graphs that preserve explanatory factors while adhering to the training data distribution. Experimental results across various datasets demonstrate the effectiveness of this approach in generating reliable and accurate explanations for GNNs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNs are powerful tools used to analyze complex relationships between entities. But how do we understand why they make certain decisions? This paper tries to answer that question by creating fake graphs that mimic real-world data, making it easier to see what’s behind the decisions. By using special algorithms and a new way of training, they can create these proxy graphs that are more like the real world, allowing us to better understand how GNNs work. |
Keywords
* Artificial intelligence * Gnn
