mlsanityData to 14 Oct 2026

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

arXiv 2601.16426 ↗First posted 23 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 ≈ 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 ≈ 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

21 of 50 references.

References · 21

  1. 2017Graph Attention Networkscited by 8,923
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  6. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  7. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
  8. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  9. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  10. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  11. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  12. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
9 more
  1. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  2. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  3. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  4. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  5. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 375
  6. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  7. 2020A Survey on Negative Transfercited by 122
  8. 2023PUFFIN: A Path-Unifying Feed-Forward Interfaced Network for Vapor Pressure Predictioncited by 8
  9. 2023Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Expertscited by 3

Built on by

Not cited yet.