平滑的
计算机科学
节点(物理)
图形
嵌入
采样(信号处理)
人工神经网络
图嵌入
代表(政治)
理论计算机科学
数据挖掘
人工智能
结构工程
滤波器(信号处理)
政治
法学
政治学
工程类
计算机视觉
作者
Thi Linh Hoang,Viet Cuong Ta
标识
DOI:10.1109/kse56063.2022.9953797
摘要
Graph neural networks (GNNs) are among the dominated approaches for learning graph structured data and are used in various applications such as social network or product recommendation. The GNN operates mainly on the message passing mechanism which a node receives related nodes information to improve its internal representation. However, when the depth of the GNN increases, the message passing mechanism cut-offs the high-frequency component of the nodes’ representation, thus leads to the over-smoothing issue. In this paper, we propose the usage of cluster-based sampling to reduce the smoothing effect of the high number of layers in GNN. Given each nodes is assigned to a specific region of the embedding space, the cluster-based sampling is expected to propagate this information to the node’s neighbour, thus improve the nodes’ expressivity. Our approach is tested with several popular GNN architecture and the experiments show that our approach could reduce the smoothing effect in comparison with the standard approaches using the Mean Average Distance metric.
科研通智能强力驱动
Strongly Powered by AbleSci AI