English

PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary

Biomolecules 2026-01-28 v1 Artificial Intelligence Machine Learning

Abstract

Molecular representation learning aims to learn vector embeddings that capture molecular structure and geometry, thereby enabling property prediction and downstream scientific applications. In many AI for science tasks, labeled data are expensive to obtain and therefore limited in availability. Under the few-shot setting, models trained with scarce supervision often learn brittle structure-property relationships, resulting in substantially higher prediction errors and reduced generalization to unseen molecules. To address this limitation, we propose PCEvo, a path-consistent representation method that learns from virtual paths through dynamic structural evolution. PCEvo enumerates multiple chemically feasible edit paths between retrieved similar molecular pairs under topological dependency constraints. It transforms the labels of the two molecules into stepwise supervision along each virtual evolutionary path. It introduces a path-consistency objective that enforces prediction invariance across alternative paths connecting the same two molecules. Comprehensive experiments on the QM9 and MoleculeNet datasets demonstrate that PCEvo substantially improves the few-shot generalization performance of baseline methods. The code is available at https://anonymous.4open.science/r/PCEvo-4BF2.

Keywords

Cite

@article{arxiv.2601.19257,
  title  = {PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary},
  author = {Kun Li and Longtao Hu and Yida Xiong and Jiajun Yu and Hongzhi Zhang and Jiameng Chen and Xiantao Cai and Jia Wu and Wenbin Hu},
  journal= {arXiv preprint arXiv:2601.19257},
  year   = {2026}
}

Comments

10 pages, 4 figures, 5 tables

R2 v1 2026-07-01T09:21:44.457Z