- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes HierExplainer and HypoExplainer for post-hoc GNN explanation that formulate explanatory subgraph discovery as latent-node inference. HierExplainer uses variational inference under a generative model, while HypoExplainer uses hypothesis testing to identify structures whose connectivity differs significantly from the background.
Critical strengths
-
The paper formulates subgraph explanation as a statistical problem, which an interesting alternative approach to commonly used XAI methods.
-
The proposed methods are well motivated and provide a potential valuable statistical way for further XAI research for GNN.
Critical weaknesses
-
The method critically relies on the assumptions, particularly the very strong assumptions 2, 4 and 6, but their validity on real-world graphs is not sufficiently examined. I'm concerned about the applicability of the method and its theoretical guarantees to real-world data.
-
The paper has no clear definition of the Saliency baseline and doesn't specify how the other baseline methods are implemented. Besides, for the GIN experiments, different methods use different target cohorts and F1 definitions (Line 789), which raises concern about whether the F1 values are comparable.
Questions for authors
-
How are the sizes of the subgraph determined for each baselines in Fig 5? For example, what is the selection threshold for GNNExplainer's edge scores? This is important for the claim that baselines' subgraph is less compact than the proposed method (line 358)
-
How do the proposed methods compare with other popular post-hoc GNN explanation methods, such as Gradient × Input, Integrated Gradients, GNN-LRP, etc.?
-
Figure 4 is too small.