Unveiling Mode Connectivity in Graph Neural Networks
It addresses the problem of understanding GNN optimization and robustness for researchers and practitioners, offering incremental insights by applying an existing concept to a new domain.
The paper investigates mode connectivity in graph neural networks (GNNs) for the first time, finding that graph structure, such as homophily, dominates this behavior and linking it to generalization with a proposed bound.
A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity, a lens for analyzing geometric properties of loss landscapes has proven insightful for other deep learning architectures, its implications for GNNs remain unexplored. This work presents the first investigation of mode connectivity in GNNs. We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs. Crucially, we demonstrate that graph structure, rather than model architecture, dominates this behavior, with graph properties like homophily correlating with mode connectivity patterns. We further establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool. Our findings further bridge theoretical insights with practical implications: they rationalize domain alignment strategies in graph learning and provide a foundation for refining GNN training paradigms.