arXiv cs.LG论文
消息传递在图神经网络回归中有多重要？GNN层级的即插即用研究
该论文指出，尽管图神经网络（GNN）广泛用于回归任务（如预测神经架构准确率），但新的消息传递（MP）层几乎仅在分类任务上进行基准测试，且回归流程通常不消融单一MP层。作者通过固定架构、损失函数和训练配方，研究了四种现有模型的选择对图级回归性能的影响，旨在量化MP层设计对回归精度的实际贡献。
这篇是正式发表的长论文，站内提供中文解读，全文请到原文阅读 PDF。
Abstract: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.