图神经网络消息传递在回归场景中的效能检验
How Much Does Message Passing Matter? A Drop-In Study of GNN Layers for Neural Network Graph Regression
浏览论文内容
中文总结 AI 辅助
本文针对回归场景被GNN评估忽视的问题，从多类回归场景检验GNN层效能，发现深度卷积GNN（尤其是GEN）比注意力型GNN更有效，经典理论型GNN也具竞争力。
中文摘要 AI 辅助
图神经网络（GNN）可对分子、媒体网络、神经网络蓝图等图数据进行有效预测，其通过消息传递技术实现预测，该技术定义了信息从节点流向邻居的方式。由于图数据类型的普遍性，新型且更优GNN的开发在机器学习领域备受关注。然而，GNN的评估与基准测试主要由分类任务驱动，因此对潜在GNN消息传递层的评估，是看其在分类场景中能否超越现有成果。相比之下，GNN同样具备执行标量回归预测的能力，但在提出新GNN时，这类问题常被忽视，且最佳分类GNN会被先验地或现成地用于回归问题。针对这一情况，本文从排名排序、误差最小化及洞察提取等多个回归场景，研究GNN层的效能。结果表明，深度卷积GNN（尤其是GEN）在这些任务上比基于注意力的GNN更有效，而其他经典的、受理论启发的GNN仍具有竞争力且高效。
英文摘要
Graph Neural Networks (GNNs) are widely used as regressors, for example to predict the accuracy of a neural architecture. Yet new message-passing (MP) layers are developed and benchmarked almost exclusively on classification tasks, and regression pipelines typically adopt a single MP layer without ablation. We ask how much the choice of MP layer matters for graph-level regression. Holding the architecture, loss and training recipe of four existing GNN regressors fixed, we substitute ten MP configurations spanning convolutional, isomorphism-based and attention-based designs. We evaluate them on eleven datasets of neural-network graphs that range from under ten to over a thousand nodes per graph and from a few hundred to over four hundred thousand samples, measuring rank correlation, prediction error, top-$k$ retrieval, latency and memory. MP choice changes results substantially, and we find that the best choice depends on graph size, training-set size and regression objective. Classical layers such as GEN, $k$-GNN and PNA match or exceed attention-based layers on small architecture graphs at lower cost, while GATv2 performs well on datasets with few large graphs.
