Knowledge-aware Contrastive Molecular Graph Learning

Abstract

Leveraging domain knowledge including fingerprints and functional groups in molecular representation learning is crucial for chemical property prediction and drug discovery. When modeling the relation between graph structure and molecular properties implicitly, existing works can hardly capture structural or property changes and complex structure, with much smaller atom vocabulary and highly frequent atoms. In this paper, we propose the Contrastive Knowledge-aware GNN (CKGNN) for self-supervised molecular representation learning to fuse domain knowledge into molecular graph representation. We explicitly encode domain knowledge via knowledge-aware molecular encoder under the contrastive learning framework, ensuring that the generated molecular embeddings equipped with chemical domain knowledge to distinguish molecules with similar chemical formula but dissimilar functions. Extensive experiments on 8 public datasets demonstrate the effectiveness of our model with a 6\% absolute improvement on average against strong competitors. Ablation study and further investigation also verify the best of both worlds: incorporation of chemical domain knowledge into self-supervised learning.

arXiv comment7 pages, 3 figures

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Towards Deeper Graph Neural Networks
• Deep Graph Contrastive Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• How Powerful are Graph Neural Networks?
• InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training

Cited by in corpus (3)

• Graph Self-Supervised Learning: A Survey
• Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction