Abstract |
This talk reviews two notable papers in self-supervised graphical neural networks; they are "Graph contrastive learning with augmentations" presented at NeurIPS 2020 and "Contrastive multi-view representation learning on graphs" presented at ICML 2020. This will be an introduction of self-supervised graphical neural networks that has emerged as one of the hottest research fields in artificial intelligence, which requires mathematical methodology across all fields of mathematics, including graph theory, algebra, topology, analysis, and geometry. |