Safe Multitask Molecular Graph Networks for Vapor Pressure and Odor Threshold Prediction

TL;DR

This paper introduces a safe multitask molecular graph network approach for predicting vapor pressure and odor threshold, emphasizing out-of-distribution robustness and systematic feature comparison.

Contribution

It proposes a novel safe multitask training method with delayed activation and gradient clipping, improving vapor pressure prediction without harming primary task performance.

Findings

PNA backbone with simple regression achieves low MSE for vapor pressure.

A20/E17 features improve odor threshold prediction.

Safe multitask training enhances primary task performance while maintaining robustness.

Abstract

We investigate two important tasks in odor-related property modeling: Vapor Pressure (VP) and Odor Threshold (OP). To evaluate the model's out-of-distribution (OOD) capability, we adopt the Bemis-Murcko scaffold split. In terms of features, we introduce the rich A20/E17 molecular graph features (20-dimensional atom features + 17-dimensional bond features) and systematically compare GINE and PNA backbones. The results show: for VP, PNA with a simple regression head achieves Val MSE $\approx$ 0.21 (normalized space); for the OP single task under the same scaffold split, using A20/E17 with robust training (Huber/winsor) achieves Val MSE $\approx$ 0.60-0.61. For multitask training, we propose a **"safe multitask"** approach: VP as the primary task and OP as the auxiliary task, using delayed activation + gradient clipping + small weight, which avoids harming the primary task and simultaneously yields the best VP generalization performance. This paper provides complete reproducible experiments, ablation studies, and error-similarity analysis while discussing the impact of data noise and method limitations.