- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes D2MoE, a Graph MoE framework that uses predictive uncertainty to adapt expert selection for each node. It maps cached predictive entropy to a node-specific probability coverage threshold and selects experts using dynamic top-p routing. The paper also provides a theoretical analysis and evaluates the method on 13 graph benchmarks, showing competitive performance against existing methods.
Critical strengths
-
The method is simple and effective. It provides a practical way to adapt expert participation based on node-level predictive uncertainty.
-
The experiments cover 13 homophilous and heterophilous datasets and compare against 20 baselines, including several Graph MoE methods.
-
The paper provides theoretical analysis, ablation studies, and routing visualizations to support the proposed method.
Critical weaknesses
-
Although the paper compares D2MoE with fixed top-p and random top-p, these methods may activate different numbers of experts. It is unclear whether the improvements come from uncertainty-guided routing or different expert participation budgets.
-
Figure 1 shows that the benefits of increasing the expert count vary across predictive entropy levels. However, it does not directly verify whether higher predictive uncertainty requires greater routing probability coverage.
-
The inference procedure is not clearly explained. Since the method relies on predictive entropy cached from previous epochs, it is unclear how the coverage thresholds are obtained during inference.
Questions for authors
-
Could the authors compare different routing strategies under similar average numbers of activated experts to better demonstrate the benefit of uncertainty guidance?
-
Could the authors provide more direct evidence that higher predictive uncertainty requires greater routing probability coverage?
-
How are the predictive entropy cache and coverage thresholds handled during inference?