一种用于图分类的类感知表示精化框架
A Class-Aware Representation Refinement Framework for Graph Classification
AI总结：
本文提出类感知表示精化框架 CARE，通过注入类表示提升图分类的类可分性和泛化能力，并在多个 GNN 骨干和数据集上验证其有效性。
摘要：
图神经网络（GNN）被广泛用于图表示学习。尽管其应用普遍，GNN 在图分类任务中存在两个缺陷：忽视图级关系以及泛化问题。在 GNN 消息传递/图池化中，每个图被单独处理，而已有的解决过拟合的方法也分别作用于每个独立的图。这使得学习到的图表示在下游分类中效果较差。本文提出了一种用于图分类任务的类感知表示精化（CARE）框架。CARE 计算简单而强大的类表示，并将其注入以引导图表示的学习，从而实现更好的类可分性。CARE 是一个即插即用的框架，具有高度灵活性，能够结合任意 GNN 骨干网络，而不会显著增加计算成本。我们还通过 Vapnik-Chervonenkis（VC）维分析从理论上证明，CARE 比其 GNN 骨干网络具有更好的泛化上界。我们在 9 个基准数据集上使用 11 个知名 GNN 骨干网络进行了大量实验，验证了 CARE 相对于其 GNN 对应方法的优越性和有效性。
英文摘要：
Graph Neural Networks (GNNs) are widely used for graph representation learning. Despite its prevalence, GNN suffers from two drawbacks in the graph classification task, the neglect of graph-level relationships, and the generalization issue. Each graph is treated separately in GNN message passing/graph pooling, and existing methods to address overfitting operate on each individual graph. This makes the graph representations learnt less effective in the downstream classification. In this paper, we propose a Class-Aware Representation rEfinement (CARE) framework for the task of graph classification. CARE computes simple yet powerful class representations and injects them to steer the learning of graph representations towards better class separability. CARE is a plug-and-play framework that is highly flexible and able to incorporate arbitrary GNN backbones without significantly increasing the computational cost. We also theoretically prove that CARE has a better generalization upper bound than its GNN backbone through Vapnik-Chervonenkis (VC) dimension analysis. Our extensive experiments with 11 well-known GNN backbones on 9 benchmark datasets validate the superiority and effectiveness of CARE over its GNN counterparts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
