论文标题
最终可以建模本地结构的图形卷积
Graph convolutions that can finally model local structure
论文作者
论文摘要
尽管在过去几年中取得了快速的进展，但最近的研究表明，现代图神经网络仍然可以在非常简单的任务中失败，例如检测小周期。这暗示了当前网络无法收集有关本地结构的信息的事实，如果下游任务严重依赖图形子结构分析，这是有问题的，就像化学的背景下一样。我们提出了对现在标准的杜松子酒卷积的非常简单的校正，该螺旋能够在计算时间和参数数量方面几乎没有成本检测小型周期。经过现实生活分子属性数据集的测试，我们的模型始终在全球和每个任务设置上的所有基线上的大型多任务数据集上的性能始终提高性能。
Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose a very simple correction to the now standard GIN convolution that enables the network to detect small cycles with nearly no cost in terms of computation time and number of parameters. Tested on real life molecule property datasets, our model consistently improves performance on large multi-tasked datasets over all baselines, both globally and on a per-task setting.
