GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916188068511744 |
|---|---|
| author | Wang, Zixiao Guo, Yuluo Zhao, Jin Zhang, Yu Yu, Hui Liao, Xiaofei Wang, Biao Yu, Ting |
| author_facet | Wang, Zixiao Guo, Yuluo Zhao, Jin Zhang, Yu Yu, Hui Liao, Xiaofei Wang, Biao Yu, Ting |
| contents | In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex network structures. We evaluate GIDN model on Open Graph Benchmark(OGB) datasets, reached an 11% higher performance than AGDN on ogbl-collab dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_01301 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction Wang, Zixiao Guo, Yuluo Zhao, Jin Zhang, Yu Yu, Hui Liao, Xiaofei Wang, Biao Yu, Ting Machine Learning Social and Information Networks In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex network structures. We evaluate GIDN model on Open Graph Benchmark(OGB) datasets, reached an 11% higher performance than AGDN on ogbl-collab dataset. |
| title | GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2210.01301 |