Summary of Graph Edits For Counterfactual Explanations: a Comparative Study, by Angeliki Dimitriou et al.
Graph Edits for Counterfactual Explanations: A comparative study
by Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Stamou
First submitted to arxiv on: 21 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 explores the use of graph neural networks (GNNs) to generate counterfactual explanations for black-box image classifiers. Counterfactuals are a popular technique that applies minimal edits to alter the prediction of a classifier, and this work focuses on extending previous research by comparing supervised and unsupervised GNN approaches. The study aims to determine whether representing input data as graphs is the most effective way to generate meaningful and efficient counterfactual explanations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to understand how an image classification model makes its predictions. One way to do this is to show you what would happen if certain features of the image were changed. This is called a counterfactual explanation. In this study, scientists compared different ways of using graph neural networks (GNNs) to create these explanations. They wanted to know which approach was best for making predictions and understanding how the model works. |
Keywords
* Artificial intelligence * Gnn * Image classification * Supervised * Unsupervised
