PolyCL: Contrastive Learning for Polymer Representation Learning via Explicit and Implicit Augmentations
This work addresses the need for high-quality polymer representations in machine learning for materials science, offering an incremental improvement through novel augmentation strategies in contrastive learning.
The authors tackled the problem of learning polymer representations for computational design and screening by introducing PolyCL, a self-supervised contrastive learning model that combines explicit and implicit augmentations, achieving better or highly competitive performances on transfer learning tasks without complex training or hyperparameter tuning.
Polymers play a crucial role in a wide array of applications due to their diverse and tunable properties. Establishing the relationship between polymer representations and their properties is crucial to the computational design and screening of potential polymers via machine learning. The quality of the representation significantly influences the effectiveness of these computational methods. Here, we present a self-supervised contrastive learning paradigm, PolyCL, for learning high-quality polymer representation without the need for labels. Our model combines explicit and implicit augmentation strategies for improved learning performance. The results demonstrate that our model achieves either better, or highly competitive, performances on transfer learning tasks as a feature extractor without an overcomplicated training strategy or hyperparameter optimisation. Further enhancing the efficacy of our model, we conducted extensive analyses on various augmentation combinations used in contrastive learning. This led to identifying the most effective combination to maximise PolyCL's performance.