APK-MRL: An Adaptive Pre-training Framework with Knowledge-enhanced for Molecular Representation Learning

Xu Gong, Qun Liu, Rui Han, Li Liu, Yike Guo, Guoyin Wang

Abstract: As a dominant pre-training paradigm, molecular contrastive learning (MCL) has been proven effective in learning molecular representations with unlabeled data. However, high data dependency and scarce domain knowledge caused by data augmentation in MCL limit the model’s generalization and performance. To address these issues, we propose an adaptive pre-training framework with knowledge-enhanced for molecular representation learning, named APK-MRL. It seamlessly integrates diverse prior information on hierarchical skeletons and the chemical semantics of molecules, aiming to obtain stronger stability and generalization. Extensive computational experiments demonstrate that APK-MRL can achieve competitive performances over state-of-the-art baselines on both drug-target interaction and molecular properties prediction tasks. All code is released at https://github.com/lukcats/APK-MRL.