mlsanityData to 7 Oct 2026

Massively Multitask Networks for Drug Discovery

arXiv 1502.02072 ↗First posted 6 Feb 2015stat.ML cs.LG cs.NEcited by 49

Not on the map. Why?

Abstract (arXiv)

Massively multitask neural architectures provide a learning framework for drug discovery that synthesizes information from many distinct biological sources. To train these architectures at scale, we gather large amounts of data from public sources to create a dataset of nearly 40 million measurements across more than 200 biological targets. We investigate several aspects of the multitask framework by performing a series of empirical studies and obtain some interesting results: (1) massively multitask networks obtain predictive accuracies significantly better than single-task methods, (2) the predictive power of multitask networks improves as additional tasks and data are added, (3) the total amount of data and the total number of tasks both contribute significantly to multitask improvement, and (4) multitask networks afford limited transferability to tasks not in the training set. Our results underscore the need for greater data sharing and further algorithmic innovation to accelerate the drug discovery process.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 14; 2023: 8; 2024: 2; 2025: 7; 2026: 3.

49 papers.

Sort:

  1. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  2. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  3. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  4. 2021A Survey on Green Deep Learningcited by 52
  5. 2021Near-optimal Representation Learning for Linear Bandits and Linear RLcited by 45
  6. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  7. 2023Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Languagecited by 44
  8. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  9. 2021Learning Attributed Graph Representations with Communicative Message Passing Transformercited by 20
  10. 2022Nearly Minimax Algorithms for Linear Bandits with Shared Representationcited by 16
  11. 2023TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphscited by 16
  12. 2022ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseasescited by 14
37 more
  1. 2022Non-Stationary Representation Learning in Sequential Linear Banditscited by 13
  2. 2023Molecular Property Prediction Based on Graph Structure Learningcited by 13
  3. 2022Structured Multi-task Learning for Molecular Property Predictioncited by 12
  4. 2021Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learningcited by 11
  5. 2023Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representationcited by 8
  6. 2022Supervised Pretraining for Molecular Force Fields and Properties Predictioncited by 7
  7. 2023On the Opportunities of Green Computing: A Surveycited by 7
  8. 2025Limits of trust in medical AIcited by 7
  9. 2021Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical Spacescited by 5
  10. 2024WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarkingcited by 5
  11. 2022BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representationcited by 4
  12. 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesiscited by 4
  13. 2023Atom-Motif Contrastive Transformer for Molecular Property Predictioncited by 4
  14. 2026Training AI Scientists to Replicate Researchcited by 4
  15. 2021SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learningcited by 3
  16. 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
  17. 2023Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learningcited by 3
  18. 2022FunQG: Molecular Representation Learning Via Quotient Graphscited by 2
  19. 2022MULTIPAR: Supervised Irregular Tensor Factorization with Multi-task Learningcited by 2
  20. 2022Substructure-Atom Cross Attention for Molecular Representation Learningcited by 2
  21. 2021Molecular Contrastive Learning of Representations via Graph Neural Networkscited by 1
  22. 2021Artificial Intelligence Narratives: An Objective Perspective on Current Developmentscited by 1
  23. 2021Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flowcited by 1
  24. 2024FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproductioncited by 1
  25. 2021Harnessing Geometric Constraints from Emotion Labels to improve Face Verificationcited by 0
  26. 2021Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Methodcited by 0
  27. 2021Bringing Atomistic Deep Learning to Prime Timecited by 0
  28. 2022FIB: A Method for Evaluation of Feature Impact Balance in Multi-Dimensional Datacited by 0
  29. 2022MLT-LE: predicting drug-target binding affinity with multi-task residual neural networkscited by 0
  30. 2025Black-Box Privacy Attacks on Shared Representations in Multitask Learningcited by 0
  31. 2025Enhancing Learning Path Recommendation via Multi-task Learningcited by 0
  32. 2025When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learningcited by 0
  33. 2025Multi-task GINN-LP for Multi-target Symbolic Regressioncited by 0
  34. 2025Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Modelscited by 0
  35. 2025Multi-Task Learning for Metal Alloy Property Prediction: An Empirical Study of Negative Transfer and Mitigation Strategiescited by 0
  36. 2026When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Predictioncited by 0
  37. 2026CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Predictioncited by 0