论文标题
使用层次集群的多尺度图卷积网络
A Multiscale Graph Convolutional Network Using Hierarchical Clustering
论文作者
论文摘要
目前未充分利用层次拓扑中包含的信息（许多网络的固有信息）。探索了一种新颖的体系结构，该体系结构通过多尺度分解来利用这些信息。树状图由Girvan-Newman分层聚类算法产生。它通过图形卷积层进行了细分和馈送，使体系结构可以学习网络的多个刻度潜在空间表示，从细性到粗粒。该体系结构在基准引用网络上进行了测试，以表明竞争性能。考虑到大量的层次网络，可能的应用包括量子分子属性预测，蛋白质界面预测和部分分化方程的多尺度计算基板。
The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised. A novel architecture is explored which exploits this information through a multiscale decomposition. A dendrogram is produced by a Girvan-Newman hierarchical clustering algorithm. It is segmented and fed through graph convolutional layers, allowing the architecture to learn multiple scale latent space representations of the network, from fine to coarse grained. The architecture is tested on a benchmark citation network, demonstrating competitive performance. Given the abundance of hierarchical networks, possible applications include quantum molecular property prediction, protein interface prediction and multiscale computational substrates for partial differential equations.
