Year: 2022
Type: conference-paper
Abstract: Graph neural networks have been widely used for a variety of learning tasks. Link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layer shallow graph auto-encoder (GAE) architectures. In this paper, we overcome the limitation of current methods for link prediction of non-Euclidean network data, which can only use shallow GAEs and variational GAEs. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs to capitalize on the intimate coupling of node and edge information in complex network data. Empirically, extensive experiments on various datasets demonstrate the competitive performance of our proposed approach. Theoretically, we prove that our deep extensions can inclusively express multiple polynomial filters with different orders. The codes of this paper are available at https://github.com/xinxingwu-uk/DGAE.
Authors: Xinxing wu, Qiang Cheng
Institution: University of Kentucky
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: Continuous and Longitudinal Monitoring of Cerebral Blood Flow and Metabolism in Freely Moving Rodents, Gene Profile Analysis of Associations between Alzheimer’s Disease and Circadian Rhythmic Patterns of Human Brain Regions Using Machine Learning, Noninvasive Noncontact High-Density Optical Imaging of Neonatal Intraventricular Hemorrhage, G7452299184, G8375851502
OpenAlex ID: W4285606307