Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs. (arXiv:2205.06783v1 [cs.LG])

Dual embodied-symbolic concept representations are the foundation for deep
learning and symbolic AI integration. We discuss the use of dual
embodied-symbolic concept representations for molecular graph representation
learning, specifically with exemplar-based contrastive self-supervised learning
(SSL). The embodied representations are learned from molecular graphs, and the
symbolic representations are learned from the corresponding Chemical knowledge
graph (KG). We use the Chemical KG to enhance molecular graphs with symbolic
(semantic) knowledge and generate their augmented molecular graphs. We treat a
molecular graph …

arxiv graph graphs learning self-supervised learning supervised learning