Training-Free Cross-Architecture Merging for Graph Neural Networks

Model merging has emerged as a powerful paradigm for combining the capabilities of distinct expert models without the high computational cost of retraining, yet current methods are fundamentally constrained to homogeneous architectures. For GNNs, however, message passing is topology-dependent and sensitive to misalignment, making direct parameter-space merging unreliable. To bridge this gap, we introduce MOSAIC (Model Operator Space Alignment for Integration & Composition), a training-free framework that lifts merging from parameter space to operator space. We formalize Universal Message Passing Mixture (UMPM), a shared operator family that expresses heterogeneous GNN layers in a common functional language. MOSAIC enables cross-architecture GNN merging (e.g., GCN$\leftrightarrow$GAT) without retraining, retaining high specialist accuracy in most cases in compatible depth settings and achieving inference speedups of $1.1\times$–$1.9\times$ over ensembles.