Knowledge-enhanced Relation Graph and Task Sampling for Few-shot Molecular Property Prediction

TL;DR

This paper introduces KRGTS, a meta-learning framework for few-shot molecular property prediction that leverages a relation graph and task sampling to better model molecule-property relationships and improve prediction accuracy.

Contribution

It proposes a novel relation graph and task sampling modules within a meta-learning framework to effectively capture complex molecule-property relationships in few-shot scenarios.

Findings

KRGTS outperforms state-of-the-art methods on five datasets.

The relation graph captures many-to-many molecule-property relationships.

Task sampling reduces noise and improves meta-learning efficiency.

Abstract

Recently, few-shot molecular property prediction (FSMPP) has garnered increasing attention. Despite impressive breakthroughs achieved by existing methods, they often overlook the inherent many-to-many relationships between molecules and properties, which limits their performance. For instance, similar substructures of molecules can inspire the exploration of new compounds. Additionally, the relationships between properties can be quantified, with high-related properties providing more information in exploring the target property than those low-related. To this end, this paper proposes a novel meta-learning FSMPP framework (KRGTS), which comprises the Knowledge-enhanced Relation Graph module and the Task Sampling module. The knowledge-enhanced relation graph module constructs the molecule-property multi-relation graph (MPMRG) to capture the many-to-many relationships between molecules and properties. The task sampling module includes a meta-training task sampler and an auxiliary task sampler, responsible for scheduling the meta-training process and sampling high-related auxiliary tasks, respectively, thereby achieving efficient meta-knowledge learning and reducing noise introduction. Empirically, extensive experiments on five datasets demonstrate the superiority of KRGTS over a variety of state-of-the-art methods. The code is available in https://github.com/Vencent-Won/KRGTS-public.