arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.15069cs.LG
收藏

图卷积最终可以模拟局部结构

Graph convolutions that can finally model local structure

AnotherBrain

Rémy Brossard, Oriel Frigo, David Dehaene

摘要:

尽管在过去几年中取得了快速进展,但最近的研究表明,现代图神经网络仍然可能在非常简单的任务中失败,比如检测小循环。这暗示了这样一个事实,即当前的网络无法捕捉关于局部结构的信息,如果下游任务严重依赖于图子结构分析,这就有问题了,就像在化学背景下一样。我们对现在标准的GIN卷积提出了一个非常简单的校正,使网络能够检测小周期,在计算时间和参数数量方面几乎没有成本。在现实生活中的分子属性数据集上进行测试,我们的模型在所有基线上,无论是在全局还是在每个任务设置上,都始终如一地提高了大型多任务数据集的性能。

英文摘要:

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.

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。

↑