Affinity uncertainty-based hard negative mining in graph contrastive learning

• Main Authors: NIU, Chaoxi, PANG, Guansong, CHEN, Ling
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Affinity learning; Estimation; graph contrastive learning (GCL); hard negative mining; Loss measurement; Measurement uncertainty; Representation learning; Task analysis; Training; Uncertainty; uncertainty estimation; Artificial Intelligence and Robotics; OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/8611; https://ink.library.smu.edu.sg/context/sis_research/article/9614/viewcontent/AffinityUncertainity_based_av.pdf
• Institution: Singapore Management University

Hard negative mining has shown effective in enhancing self-supervised contrastive learning (CL) on diverse data types, including graph CL (GCL). The existing hardness-aware CL methods typically treat negative instances that are most similar to the anchor instance as hard negatives, which helps impro...