2022.1.24 第三次 论文速览

文章目录

• Graph-based High-order Relation Modeling for Long-term Action Recognition（CVPR2021）
• • 目的
  • 方法
• GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs (ICDM2021)
• • 目的
  • 方法
• Predicting Customer Value with Social Relationships via Motif-based Graph Attention Networks (WWW2021)
• • 目的
  • 方法

Graph-based High-order Relation Modeling for Long-term Action Recognition（CVPR2021）

目的

long-term action recognition

方法

其中GHRM module

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs (ICDM2021)

目的

Node Classification in Dynamic Graphs

方法

considering the snapshot at each timestep to be a “channel” of data, analogous to the RGB color channels in image datasets. then use Squeeze-and-Excitation (SE) to capture the temporal information.

Predicting Customer Value with Social Relationships via Motif-based Graph Attention Networks (WWW2021)

目的

Predicting Customer Value，
Using Motif-based Multi-view Graph Attention Networks with Gated Fusion

方法

总体框架

motif network construction：

现实意义：

标签：Customer,Node,Predicting,based,23,Graph,Attention,速览,2022.1
来源： https://blog.csdn.net/weixin_46782905/article/details/122658527