Geometric Pooling: maintaining more useful information
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929462168256512 |
|---|---|
| author | Xu, Hao Liu, Jia Shen, Yang Lou, Kenan Bao, Yanxia Zhang, Ruihua Zhou, Shuyue Zhao, Hongsen Wang, Shuai |
| author_facet | Xu, Hao Liu, Jia Shen, Yang Lou, Kenan Bao, Yanxia Zhang, Ruihua Zhou, Shuyue Zhao, Hongsen Wang, Shuai |
| contents | 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 useful information and can contribute considerably to the final decision. To maintain more useful information, a novel pooling technology, called Geometric Pooling (GP), was proposed to contain 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%\sim5% with fewer parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_12341 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Geometric Pooling: maintaining more useful information Xu, Hao Liu, Jia Shen, Yang Lou, Kenan Bao, Yanxia Zhang, Ruihua Zhou, Shuyue Zhao, Hongsen Wang, Shuai Computer Vision and Pattern Recognition 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 useful information and can contribute considerably to the final decision. To maintain more useful information, a novel pooling technology, called Geometric Pooling (GP), was proposed to contain 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%\sim5% with fewer parameters. |
| title | Geometric Pooling: maintaining more useful information |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.12341 |