mlsanityData to 7 Oct 2026

Ranking over Regression for Bayesian Optimization and Molecule Selection

arXiv 2410.09290 ↗First posted 11 Oct 2024cs.LG cs.AI stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Bayesian optimization (BO) has become an indispensable tool for autonomous decision-making across diverse applications from autonomous vehicle control to accelerated drug and materials discovery. With the growing interest in self-driving laboratories, BO of chemical systems is crucial for machine learning (ML) guided experimental planning. Typically, BO employs a regression surrogate model to predict the distribution of unseen parts of the search space. However, for the selection of molecules, picking the top candidates with respect to a distribution, the relative ordering of their properties may be more important than their exact values. In this paper, we introduce Rank-based Bayesian Optimization (RBO), which utilizes a ranking model as the surrogate. We present a comprehensive investigation of RBO's optimization performance compared to conventional BO on various chemical datasets. Our results demonstrate similar or improved optimization performance using ranking models, particularly for datasets with rough structure-property landscapes and activity cliffs. Furthermore, we observe a high correlation between the surrogate ranking ability and BO performance, and this ability is maintained even at early iterations of BO optimization when using ranking surrogate models. We conclude that RBO is an effective alternative to regression-based BO, especially for optimizing novel chemical compounds.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 50 of its 109 references that are in the map. First posted on arXiv 11 Oct 2024.

Builds on

50 of 109 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  11. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  12. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
38 more
  1. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  2. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  3. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  4. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  5. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  6. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  7. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  8. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  9. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  10. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
  11. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  12. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  13. 2019A Deep Look into Neural Ranking Models for Information Retrievalcited by 79
  14. 2017Preferential Bayesian Optimizationcited by 72
  15. 2024Variational Bayesian Last Layerscited by 67
  16. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  17. 2020Accelerating high-throughput virtual screening through molecular pool-based active learningcited by 59
  18. 2022Pareto Set Learning for Neural Multi-objective Combinatorial Optimizationcited by 56
  19. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
  20. 2022GAUCHE: A Library for Gaussian Processes in Chemistrycited by 40
  21. 2021JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Designcited by 31
  22. 2021Pairwise Supervised Contrastive Learning of Sentence Representationscited by 31
  23. 2020Learnable Uncertainty under Laplace Approximationscited by 29
  24. 2019Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learningcited by 21
  25. 2020Top-k Ranking Bayesian Optimizationcited by 21
  26. 2020Gaussian Process Molecule Property Prediction with FlowMOcited by 18
  27. 2020Data-Driven Discovery of Molecular Photoswitches with Multioutput Gaussian Processescited by 14
  28. 2021Assigning Confidence to Molecular Property Predictioncited by 14
  29. 2022Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUScited by 10
  30. 2023Exploring QSAR Models for Activity-Cliff Predictioncited by 9
  31. 2023Data Commonscited by 8
  32. 2023On the role of Model Uncertainties in Bayesian Optimizationcited by 7
  33. 2018Sequential Preference-Based Optimizationcited by 5
  34. 2020A benchmark study on reliable molecular supervised learning via Bayesian learningcited by 5
  35. 2023Deep Ranking Ensembles for Hyperparameter Optimizationcited by 5
  36. 2023Pairwise Similarity Learning is SimPLEcited by 4
  37. 2020Accelerated Convergence for Counterfactual Learning to Rankcited by 3
  38. 2024Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025El Agente: An Autonomous Agent for Quantum Chemistrycited by 43
  2. 2025Post Hoc Regression Refinement via Pairwise Rankingscited by 0
  3. 2025Quantile-Scaled Bayesian Optimization Using Rank-Only Feedbackcited by 0
  4. 2026Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimizationcited by 0