arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.07524cs.LGcs.AIstat.ML
收藏

节点掩蔽:使图神经网络更好地泛化和扩展

Node Masking: Making Graph Neural Networks Generalize and Scale Better

Facebook AI;Facebook

Pushkar Mishra, Aleksandra Piktus, Gerard Goossen, Fabrizio Silvestri

摘要:

图神经网络(GNN)在最近一段时间受到了广泛的关注。从早期的光谱架构只能在无向图上操作的每一个转换学习范式到目前最先进的空间架构,可以归纳地应用于任意图,GNN已经看到了来自研究界的重大贡献。在本文中,我们利用一些理论工具来更好地可视化最先进的空间GNN执行的操作。我们分析了这些架构的内部工作原理,并引入了一个简单的概念,节点掩码,使它们能够更好地泛化和扩展。为了从经验上验证这一概念,我们在一些广泛使用的数据集上进行了几次实验,用于在转导和归纳设置中进行节点分类,从而为未来的研究奠定了强有力的基准。

英文摘要:

Graph Neural Networks (GNNs) have received a lot of interest in the recent times. From the early spectral architectures that could only operate on undirected graphs per a transductive learning paradigm to the current state of the art spatial ones that can apply inductively to arbitrary graphs, GNNs have seen significant contributions from the research community. In this paper, we utilize some theoretical tools to better visualize the operations performed by state of the art spatial GNNs. We analyze the inner workings of these architectures and introduce a simple concept, Node Masking, that allows them to generalize and scale better. To empirically validate the concept, we perform several experiments on some widely-used datasets for node classification in both the transductive and inductive settings, hence laying down strong benchmarks for future research.

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。

↑