提出PyG中ogbn-proteins的可复现边感知基线，优化特征聚合与消息传递策略。
Edge-aware baselines for ogbn-proteins in PyTorch Geometric: species-wise normalization, post-hoc calibration, and cost-accuracy trade-offs
- 采用基于求和的边到节点特征聚合方式
- 批归一化在AUC上表现最佳，条件层归一化提升F1和校准性
- 后处理温度调节与标签阈值显著改善分类质量，适合实际部署
我们在PyTorch Geometric中为ogbn-proteins构建了可复现的边感知基线。研究两个主导实践的设计选择：(i) 如何将8维边证据聚合为节点输入，(ii) 边在消息传递中的使用方式。最强基线为基于求和的GraphSAGE。对比了层归一化（LN）、批归一化（BN）和物种感知的条件层归一化（CLN），并报告计算成本（时间、显存、参数量）与精度（ROC-AUC）及决策质量。在主实验设置下（隐藏层512，3层，3个随机种子），求和始终优于均值和最大值；BN获得最高AUC，而CLN在保持AUC前沿的同时提升了阈值化F1。后处理中每标签温度缩放与阈值调整显著提升micro-F1与期望校准误差（ECE），AUC变化微小；轻量级标签相关性平滑带来额外小幅提升。所有实验所用标准化工具与脚本均已公开。
原文摘要 · Abstract (English)
We present reproducible, edge-aware baselines for ogbn-proteins in PyTorch Geometric (PyG). We study two system choices that dominate practice: (i) how 8-dimensional edge evidence is aggregated into node inputs, and (ii) how edges are used inside message passing. Our strongest baseline is GraphSAGE with sum-based edge-to-node features. We compare LayerNorm (LN), BatchNorm (BN), and a species-aware Conditional LayerNorm (CLN), and report compute cost (time, VRAM, parameters) together with accuracy (ROC-AUC) and decision quality. In our primary experimental setup (hidden size 512, 3 layers, 3 seeds), sum consistently beats mean and max; BN attains the best AUC, while CLN matches the AUC frontier with better thresholded F1. Finally, post-hoc per-label temperature scaling plus per-label thresholds substantially improves micro-F1 and expected calibration error (ECE) with negligible AUC change, and light label-correlation smoothing yields small additional gains. We release standardized artifacts and scripts used for all of the runs presented in the paper.
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。