Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs

TL;DR

This paper introduces a novel contrastive self-supervised learning approach that combines embodied molecular graph representations with symbolic chemical knowledge graphs to improve molecular graph understanding.

Contribution

It proposes a dual embodied-symbolic contrastive SSL framework that integrates semantic knowledge from chemical KGs with molecular graph representations.

Findings

Enhanced molecular graph representations with symbolic knowledge

Improved performance in molecular property prediction tasks

Effective augmentation of molecular graphs using chemical knowledge

Abstract

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 and its semantically augmented molecular graph as exemplars of the same semantic class, and use the pairs as positive pairs in exemplar-based contrastive SSL.