A Model-Agnostic Graph Neural Network for Integrating Local and Global Information
This addresses interpretability and representation issues in GNNs for graph-focused tasks, offering a novel framework with potential applications in scientific domains like neuroscience, though it appears incremental as it builds on existing GNN concepts.
The paper tackles the lack of interpretability and limited representation learning in Graph Neural Networks (GNNs) by proposing MaGNet, a model-agnostic framework that integrates local and global information, achieving superior performance in simulated data and a real-world brain activity case study.
Graph Neural Networks (GNNs) have achieved promising performance in a variety of graph-focused tasks. Despite their success, however, existing GNNs suffer from two significant limitations: a lack of interpretability in their results due to their black-box nature, and an inability to learn representations of varying orders. To tackle these issues, we propose a novel Model-agnostic Graph Neural Network (MaGNet) framework, which is able to effectively integrate information of various orders, extract knowledge from high-order neighbors, and provide meaningful and interpretable results by identifying influential compact graph structures. In particular, MaGNet consists of two components: an estimation model for the latent representation of complex relationships under graph topology, and an interpretation model that identifies influential nodes, edges, and node features. Theoretically, we establish the generalization error bound for MaGNet via empirical Rademacher complexity, and demonstrate its power to represent layer-wise neighborhood mixing. We conduct comprehensive numerical studies using simulated data to demonstrate the superior performance of MaGNet in comparison to several state-of-the-art alternatives. Furthermore, we apply MaGNet to a real-world case study aimed at extracting task-critical information from brain activity data, thereby highlighting its effectiveness in advancing scientific research.