Estimating Subgraph Importance with Structural Prior Domain Knowledge

2026-05-12

AI Summary

This work addresses the challenge of effectively estimating the importance of subgraphs for graph-level tasks without access to ground-truth labels or reliance on the specific architecture of a graph neural network’s output layer. To this end, the authors formulate the problem as a linear Group Lasso regression in the embedding space and introduce structural priors—used here for the first time—to guide the solution. The proposed approach eliminates dependence on both task-specific labels and model architectures while naturally extending to the identification of critical nodes. Extensive experiments on multiple real-world graph datasets demonstrate that the method significantly outperforms existing baselines, confirming its effectiveness and strong generalization capability in assessing both subgraph and node importance.

Abstract

We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it does not require access to ground-truth target labels. Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation. Furthermore, we extend our method to identify important nodes within the graph.

Problem

• subgraph importance
• Graph Neural Networks
• domain knowledge
• graph-level tasks
• embedding space

Innovation

• subgraph importance
• Group Lasso
• structural prior
• Graph Neural Networks
• embedding space