FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models
This work addresses the need for interpretable surrogate models in scientific applications like atmospheric and fluid dynamics, offering a domain-specific improvement for researchers in these fields.
The paper tackled the problem of obscured spatial influences of different features in multivariate prediction tasks with traditional GNNs by introducing FIGNN, a novel GNN architecture with feature-specific pooling and mask-based regularization, achieving competitive predictive performance and revealing physically meaningful spatial patterns in surrogate modeling of atmospheric and fluid dynamics systems.
This work presents a novel graph neural network (GNN) architecture, the Feature-specific Interpretable Graph Neural Network (FIGNN), designed to enhance the interpretability of deep learning surrogate models defined on unstructured grids in scientific applications. Traditional GNNs often obscure the distinct spatial influences of different features in multivariate prediction tasks. FIGNN addresses this limitation by introducing a feature-specific pooling strategy, which enables independent attribution of spatial importance for each predicted variable. Additionally, a mask-based regularization term is incorporated into the training objective to explicitly encourage alignment between interpretability and predictive error, promoting localized attribution of model performance. The method is evaluated for surrogate modeling of two physically distinct systems: the SPEEDY atmospheric circulation model and the backward-facing step (BFS) fluid dynamics benchmark. Results demonstrate that FIGNN achieves competitive predictive performance while revealing physically meaningful spatial patterns unique to each feature. Analysis of rollout stability, feature-wise error budgets, and spatial mask overlays confirm the utility of FIGNN as a general-purpose framework for interpretable surrogate modeling in complex physical domains.