Summary of Graph Neural Network Causal Explanation Via Neural Causal Models, by Arman Behnam et al.
Graph Neural Network Causal Explanation via Neural Causal Models
by Arman Behnam, Binghui Wang
First submitted to arxiv on: 12 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
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 novel Graph Neural Network (GNN) causal explainer, called {name}, which identifies the important subgraph responsible for a given graph’s prediction. Unlike existing GNN explainers based on association, which can be prone to spurious correlations, {name} utilizes causal inference to uncover the underlying causal structure of the graph. The method consists of three steps: building a structural causal model (SCM) for the graph, using a neural causal model (NCM) to enable cause-effect calculation among nodes, and then identifying the subgraph that causally explains the GNN predictions. Experimental results on multiple synthetic and real-world graphs demonstrate the effectiveness of {name} in accurately identifying the groundtruth explanations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to explain how graph neural networks make decisions. It’s like trying to figure out why a certain group of people might be more likely to buy a product, rather than just saying “oh, they’re all buying it because they like it”. The researchers created a new method called {name} that helps us understand which parts of the graph are most important for making predictions. They tested this on lots of different graphs and showed that it works really well. |
Keywords
» Artificial intelligence » Gnn » Graph neural network » Inference
