GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

作     者：Wang, Zixiao Guo, Yuluo Zhao, Jin Zhang, Yu Yu, Hui Liao, Xiaofei Wang, Biao Yu, Ting 

作者机构：National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2022年

核心收录：

主　　题：Complex networks 

摘      要：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. Copyright © 2022, The Authors. All rights reserved.