Graph contrastive learning with stable and scalable spectral encoding

• Main Authors: BO, Deyu, FANG, Yuan, LIU, Yang, SHI, Chuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Graph contrastive learning; spectral encoding; spatial-spectral graph neural networks; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8333; https://ink.library.smu.edu.sg/context/sis_research/article/9336/viewcontent/NeruIPS_2023.pdf
• Institution: Singapore Management University

Graph contrastive learning (GCL) aims to learn representations by capturing the agreements between different graph views. Traditional GCL methods generate views in the spatial domain, but it has been recently discovered that the spectral domain also plays a vital role in complementing spatial views....