提升预传播图神经网络的表达能力，实现高效训练与高精度的平衡。
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
- 设计鲁棒的图扩散算子用于预处理，增强节点特征传播效果。
- 引入少样本隐藏状态重传播机制，在训练中提升模型表现。
- 在异质图上性能接近消息传递模型，同时保持高效训练速度。
预传播图神经网络（PPGNNs）将节点特征传播与变换解耦：图扩散仅作为预处理执行一次，训练简化为每个节点的密集变换。这一设计支持小批量训练、避免重复的稀疏矩阵乘法，更适配现代加速器对密集计算的优化。然而其表达能力尚不明确，实证结果表明，其在常用图基准测试中，尤其是异质图上，与消息传递型图神经网络存在差距。本文提出一套鲁棒的图扩散算子用于预处理，并引入少样本隐藏状态重传播机制。该方法显著提升了PPGNN的验证与测试准确率，使其在保持训练效率的同时，达到与消息传递型GNN相当的性能。
原文摘要 · Abstract (English)
Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to dense per-node transformations. This design enables mini-batch training without inter-node dependencies, avoids repeated sparse matrix--matrix multiplications, and better matches modern accelerators optimized for dense compute. However, their expressivity remains unclear, and empirical results show a gap between PPGNNs and their message-passing counterparts on commonly used graph benchmarks, especially heterophilic ones. In this paper, we propose a suite of robust graph diffusion operators for preprocessing and a few-shot hidden-state re-propagation scheme during training. Our methods improve the validation and test accuracy of PPGNNs, enabling them to match the accuracy of message-passing GNNs while maintaining training efficiency.
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。