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 H-GRAMA (Heterogeneous Graph Routing and Message Alignment), 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. H-GRAMA enables cross-architecture GNN merging (e.g., GCN to GAT) without retraining, retaining high specialist accuracy in most cases in compatible depth settings and achieving inference speedups of 1.2x to 1.9x over ensembles.

翻译：模型融合已成为一种强大的范式，能够在不承担重新训练的高昂计算成本的前提下，整合不同专家模型的能力，然而现有方法从根本上受限于同构架构。对于图神经网络而言，消息传递依赖于拓扑结构且对错位敏感，使得直接在参数空间进行融合并不可靠。为弥合这一差距，我们提出了H-GRAMA（异构图路由与消息对齐），这是一个无需训练的框架，将融合从参数空间提升至算子空间。我们形式化了通用消息传递混合，这是一个共享的算子族，能够以通用的函数语言表达异构的图神经网络层。H-GRAMA实现了跨架构图神经网络融合（例如，从GCN到GAT），无需重新训练，在大多数兼容深度配置下保持了较高的专家模型精度，并实现了相较于集成方法1.2倍至1.9倍的推理加速。