无需训练即可合并不同架构的图神经网络，保留高精度并提速。
Training-Free Cross-Architecture Merging for Graph Neural Networks
- 将模型合并从参数空间转至操作符空间，解决异构图网络对齐难题。
- 在多数深度设置下保持专家模型高精度，推理速度提升1.2倍至1.9倍。
- 适用于需快速集成多种GNN模型的场景，如多源知识融合、部署优化。
模型合并已成为一种强大范式，可在不付出高昂重训成本的前提下整合多个专家模型的能力，但现有方法仅限于同构架构。对于图神经网络（GNN），消息传递依赖拓扑结构且对错位敏感，直接在参数空间合并不可靠。为此，我们提出H-GRAMA（异构图路由与消息对齐）框架，将合并从参数空间转移到操作符空间。我们形式化了通用消息传递混合（UMPM），一种可表达异构GNN层的共享操作符族，以统一函数语言表示。H-GRAMA实现跨架构的GNN合并（如GCN到GAT），无需重训，在兼容深度设置下大多保持高专业精度，并实现相比集成模型1.2x至1.9x的推理加速。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。