pyg-team/pytorch_geometric
Ver no GitHubExplanability for Heterogeneous Graphs
Open
#5.630 aberto em 7 de out. de 2022
0 - Priority P0explainfeaturehelp wanted
Métricas do repositório
- Stars
- (19.985 stars)
- Métricas de merge de PR
- (Mesclagem média 35d 1h) (14 fundiu PRs em 30d)
Description
🚀 Heterogeneous Graph Explanation
Explainability support for heterogeneous graphs. There exist simple ways to adapt current explainability methods into heterogeneous graphs. For example, we can use gradient-based methods by taking gradient with respect to adjacencies (edge_index) of different message types. We can also adapt GNNExplainer by creating a mask corresponding to each of the edge_index for different message types.
Thanks for the good points@Padarn and @wsad1! I'll discuss offline and update this issue with more details for things like HGTConv in a few days.
Tasks:
- Extension of the current explainability framework to work for HeteroData objects.
- Incorporate captum-based explainability implementation (such as SHAP, DeepLIFT) for HeteroData.
- Potential extension to hypergraph use cases (where the graph data is represented as nodes and a set of hyperedges which can connect more than 2 nodes).
Alternatives
No response
Additional context
No response