Summary of Towards Few-shot Self-explaining Graph Neural Networks, by Jingyu Peng et al.
Towards Few-shot Self-explaining Graph Neural Networks
by Jingyu Peng, Qi Liu, Linan Yue, Zaixi Zhang, Kai Zhang, Yunhao Sha
First submitted to arxiv on: 14 Aug 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 The proposed Meta-learned Self-Explaining GNN (MSE-GNN) is a novel framework that generates explanations to support predictions in few-shot scenarios. It adopts a two-stage self-explaining structure consisting of an explainer and a predictor. The explainer imitates the attention mechanism of humans to select the explanation subgraph, while the predictor mimics the decision-making process making predictions based on the generated explanation. MSE-GNN can achieve remarkable performance on new few-shot tasks with a novel meta-training process and designed mechanism exploiting task information. It outperforms existing methods on four datasets in terms of prediction accuracy and explanation quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MSE-GNN is a special kind of computer model that helps doctors and scientists understand why it makes certain decisions. Usually, these models just make predictions without explaining why. MSE-GNN is different because it can both make predictions and explain its thought process. This is useful in medicine where we need to understand how the model arrived at a diagnosis or treatment recommendation. The new method is called Meta-learned Self-Explaining GNN (MSE-GNN) and it’s good at making decisions and providing explanations even when it only has a little bit of information. |
Keywords
» Artificial intelligence » Attention » Few shot » Gnn » Mse
