.png){kind=icon}
返回
SSPool: A Simple Siamese Framework for Graph Infomax Pooling
.png){kind=icon}
PRE
AI
DOI：10.1109/TNSE.2023.3300878.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph pooling plays an indispensable role in graph representation learning by aggregating the node representations on the graph into a compact form. However, the existing graph pooling models based on mutual information maximization all need to construct negative samples and usually only consider local neighborhood information. In this article, we propose a novel coarsening graph infomax pooling method called SSPool, which selects the most informative subset of nodes as the pooled graph by neural estimation of the mutual information between the coarsened graph and the augmented coarsening graph. To maximize the neural estimation of mutual information, we propose a self-attention-based top-k method to learn the coarsened graph, while we use edge perturbation to augment the coarsened graph and a simple Siamese network framework to help the coarsened graph to get a better representation. Extensive experimental results show that our method outperforms previous state-of-the-art methods on eight benchmark data sets.
Keyword:
Mutual information
Task analysis
Representation learning
Computational modeling
Topology
Graph neural networks
Spectral analysis
Graph representation learning
graph pooling
mutual information maximization
simple Siamese networks
期刊
I
IF:
7.9
论文数:
2.5K
被引数:
10.0K
机构
引用论文
Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
.png){kind=icon}
PREAI
分享收藏分享收藏
查看更多内容