Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which would ignore the distinct impacts from different neighbors when aggregating their features to update a ...

基于洪泽湖2013-2022年水质时空异质性分析，提出融合STL分解、图卷积网络（GCN）和随机森林（RF）的新型可解释WQImin框架，显著提升复杂水文湖区的水质评估精度与泛化能力，明确不同区域关键参数组合及空间交互机制。 南水北调工程对洪泽湖水质时空演变规律 ...

Giulia Livieri sets out remarkable new research with results that clarify how learning works on complex graphs and how quickly any method (including Graph Convolutional Networks) can learn from them, ...