Geometric Pooling: Maintaining More Representative Information

Geometric Pooling: Maintaining More Representative Information

Graph Pooling technology plays an important role in graph node classification tasks. Sorting pooling technologies maintain large-value units for pooling graphs of varying sizes. However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of uni...

Full description

Bibliographic Details
Main Authors: Hao Xu, Jia Liu, Yang Shen, Kenan Lou, Yanxia Bao, Ruihua Zhang, Shuyue Zhou, Hongsen Zhao, Xinmiao Zhu, Shuai Wang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Graph neural networks
pooling
similarity
Online Access:https://ieeexplore.ieee.org/document/10496995/

Internet

https://ieeexplore.ieee.org/document/10496995/

Similar Items