mlsanityData to 14 Oct 2026

Structured Multi-task Learning for Molecular Property Prediction

arXiv 2203.04695 ↗First posted 22 Feb 2022q-bio.BM cs.LG stat.MLcited by 12

Not on the map. Why?

Abstract (arXiv)

Multi-task learning for molecular property prediction is becoming increasingly important in drug discovery. However, in contrast to other domains, the performance of multi-task learning in drug discovery is still not satisfying as the number of labeled data for each task is too limited, which calls for additional data to complement the data scarcity. In this paper, we study multi-task learning for molecular property prediction in a novel setting, where a relation graph between tasks is available. We first construct a dataset (ChEMBL-STRING) including around 400 tasks as well as a task relation graph. Then to better utilize such relation graph, we propose a method called SGNN-EBM to systematically investigate the structured task modeling from two perspectives. (1) In the latent space, we model the task representations by applying a state graph neural network (SGNN) on the relation graph. (2) In the output space, we employ structured prediction with the energy-based model (EBM), which can be efficiently trained through noise-contrastive estimation (NCE) approach. Empirical results justify the effectiveness of SGNN-EBM. Code is available on https://github.com/chao1224/SGNN-EBM.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 23 of its 51 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

23 of 51 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  5. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  6. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  8. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  10. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  11. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  12. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 320
11 more
  1. 2021How to Train Your Energy-Based Modelscited by 274
  2. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  3. 2016A Theory of Generative ConvNetcited by 174
  4. 2020Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Modelscited by 169
  5. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  6. 2018N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Moleculescited by 93
  7. 2020Generalized Energy Based Modelscited by 73
  8. 2015Structured Prediction Energy Networkscited by 59
  9. 2015Massively Multitask Networks for Drug Discoverycited by 49
  10. 2014Multi-task Neural Networks for QSAR Predictionscited by 17
  11. 2014Generative Modeling of Convolutional Neural Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 9; 2024: 0; 2025: 3.

12 papers.

  1. 2023A Text-guided Protein Design Frameworkcited by 64
  2. 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materialscited by 22
  3. 2023Improving Domain Generalization with Domain Relationscited by 14
  4. 2023Knowledge-augmented Graph Machine Learning for Drug Discovery: A Surveycited by 6
  5. 2023Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Taskscited by 6
  6. 2023MolKD: Distilling Cross-Modal Knowledge in Chemical Reactions for Molecular Property Predictioncited by 4
  7. 2023Learning to Group Auxiliary Datasets for Moleculecited by 3
  8. 2025Data Fusion of Deep Learned Molecular Embeddings for Property Predictioncited by 2
  9. 2025ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Predictioncited by 1
  10. 2023Multi-Task Learning with Loop Specific Attention for CDR Structure Predictioncited by 0
  11. 20233D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillationcited by 0
  12. 2025Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Predictioncited by 0