BriefGPT.xyz
Feb, 2022
有向图自编码器
Directed Graph Auto-Encoders
HTML
PDF
Georgios Kollias, Vasileios Kalantzis, Tsuyoshi Idé, Aurélie Lozano, Naoki Abe
TL;DR
本文介绍了一种新型自动编码器，用于有向图的建模，该模型使用带参数图卷积网络(GCN)层作为编码器和不对称内积解码器, 学习了一对可解释的节点潜在表征，并在几个流行的网络数据集中展示了该模型在有向链接预测任务上取得了优异的性能。
Abstract
We introduce a new class of
auto-encoders
for
directed graphs
, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable
→