Year: 2026
Type: preprint
Abstract: Molecular representations are inherently task-dependent, yet most pre-trained molecular encoders are not. Task conditioning promises representations that reorganize based on task descriptions, but existing approaches rely on expensive labeled data. We show that weak supervision on programmatically derived molecular motifs is sufficient. Our Adaptive Chemical Embedding Model (ACE-Mol) learns from hundreds of motifs paired with natural language descriptors that are cheap to compute, trivial to scale. Conventional encoders slowly search the embedding space for task-relevant structure, whereas ACE-Mol immediately aligns its representations with the task. ACE-Mol achieves state-of-the-art performance across molecular property prediction benchmarks with interpretable, chemically meaningful representations.
Source: arXiv (Cornell University)
Authors: Prastalo, Gordan, Jablonka, Kevin Maik
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7128080919
Cites:
Cited by:
Related to: