# Active Learning Enables Generation of Molecules that Advance the Known Pareto Front

arXiv: https://arxiv.org/abs/2501.02059 · HTML: https://mlsanity.com/paper/2501.02059/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 61 references that are in the map.
- First posted on arXiv 3 Jan 2025.

## Builds on (most cited first, 19 of 19)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2006.05078/) (2020)
- [The Synthesizability of Molecules Proposed by Generative Models](https://mlsanity.com/paper/2002.07007/) (2020)
- [Regression Transformer: Concurrent sequence regression and generation for molecular language modeling](https://mlsanity.com/paper/2202.01338/) (2022)
- [JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design](https://mlsanity.com/paper/2106.04011/) (2021)
- [AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance](https://mlsanity.com/paper/2003.12476/) (2020)
- [AiiDA: Automated Interactive Infrastructure and Database for Computational Science](https://mlsanity.com/paper/1504.01163/) (2015)
- [Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design](https://mlsanity.com/paper/2209.12487/) (2022)
- [Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study](https://mlsanity.com/paper/2401.08032/) (2024)
- [Inverse Design of Copolymers Including Stoichiometry and Chain Architecture](https://mlsanity.com/paper/2410.02824/) (2024)
- [Generative Active Learning for the Search of Small-molecule Protein Binders](https://mlsanity.com/paper/2405.01616/) (2024)

## Built on by (most cited first, 2 of 2)

- [ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods](https://mlsanity.com/paper/2505.22494/) (2025)
- [ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion](https://mlsanity.com/paper/2606.04468/) (2026)

## Abstract (arXiv)

Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the properties of the structures represented in the training distribution. We find that this limitation arises not only from the molecule generation process itself, but also from the poor generalization capabilities of molecular property predictors. We address this challenge by creating a closed-loop molecule generation pipeline with iterative retraining on new quantum chemical simulation data. Compared against static, single-pass generative modeling approaches, only our closed-loop iterative workflow generates molecules with properties extending beyond the training distribution (up to 0.44 standard deviations beyond the original range) and achieves a 79% improvement in out-of-distribution molecule classification accuracy. Furthermore, by conditioning molecular generation on thermodynamic stability data obtained during the iterative loop, the proportion of stable and hence potentially synthesizable molecules generated is 3.5x higher than the next-best model.