用几何粗粒化训练小图，直接部署大图，无需重训。
Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
- 通过几何粗粒化对图进行降维，训练后直接迁移到原图。
- 在真实与合成网络上，小图训练保留了大图的大部分预测性能。
- 结构相似性比图大小更关键，适合大规模图学习场景。
图神经网络（GNN）可在大规模图上运行，但当节点数达百万级时易受基础设施限制，通常需可扩展训练技术处理更大规模图。核心问题在于：在小规模图上训练的模型能否无需重训直接部署到全分辨率图？本文提出零样本迁移协议——在几何粗粒化（GR）生成的简化图上训练GNN，直接将权重迁移至原始图。在合成及真实网络中，该方法在显著降低训练成本的同时，保持了原尺度的大部分预测性能。进一步发现，跨尺度的表征与预测轨迹仍具对齐性。结果表明，结构相似性可能比网络规模更影响GNN可迁移性，为构建尺度等变图架构开辟新路径。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques for even larger graphs. This raises a central question: when can a model trained on a smaller, scaled-down replica of a graph be deployed on the full-resolution graph without retraining? We introduce a zero-shot transfer protocol in which a GNN is trained on a graph coarse-grained by geometric renormalization (GR), and the resulting weights are transferred directly to the original network. Across synthetic and real-world networks, training on GR scaled-down replicas preserves much of the original-scale predictive performance while significantly reducing training cost. We further find that learned representations and predictive trajectories remain aligned across scales. These findings suggest that structural similarity may be more important than network size in determining GNN transferability, opening a path toward scale-equivariant graph architectures.
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。