Year: 2022
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Wang, Zixiao, Guo, Yuluo, Zhao, Jin, Zhang, Yu, Yu, Hui, Liao, Xiaofei, Wang, Biao, Yu, Ting
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4302305850