.png){kind=icon}
返回
Geometric Pooling: Maintaining More Representative Information
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3387703.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 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 units dropped by sorting pooling are negative-value units that contain representative information and can contribute considerably to the final decision. To maintain more representative information, we proposed a novel pooling technology, called Geometric Pooling (GP), containing the unique node features with negative values by measuring the similarity of all node features. We reveal the effectiveness of GP from the entropy reduction view. The experiments were conducted on TUdatasets to show the effectiveness of GP. The results showed that the proposed GP outperforms the SOTA graph pooling technologies by 1%similar to 5% with fewer parameters.
Keyword:
Sorting
Smoothing methods
Entropy
Training data
Convolutional neural networks
Topology
Task analysis
Graph neural networks
pooling
similarity
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
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
PREAI
分享收藏Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors
OAAI
OAAI分享收藏Research on the Efficiency of Wireless Power Transfer System Based on Multi-Auxiliary Transmitting Coils基于多辅助发射线圈的无线电能传输系统效率研究
PREAI
分享收藏
查看更多内容