1 个仓库
Awesome GitHub RepositoriesGraph
Methods for analyzing and visualizing the internal workings of graph-based neural networks.
Distinct from Neural Network Interpretability: Distinct from Neural Network Interpretability: specifically targets graph-based models and structural pattern analysis.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Graph. Refine with filters or upvote what's useful.
Awesome Graph GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- rexying/gnn-model-explainer
RexYing/gnn-model-explainer
1,051在 GitHub 上查看This toolkit serves as a framework for interpreting the decision-making processes of graph neural networks. It functions as a library for analyzing how these models process complex network data, providing methods to identify the specific node attributes and structural patterns that influence predictive outcomes. The project distinguishes itself by employing mask-optimized subgraph extraction and gradient-based attribution mapping to isolate the minimal components of a graph that preserve a model's original prediction. By separating graph processing layers from explanation logic, the architect
Analyzes how graph-based machine learning models make predictions by identifying influential nodes and structural patterns.
Python
