Sample Efficient Generative Molecular Optimization with Joint Self-Improvement

• URL: http://arxiv.org/abs/2602.10984v1
• Date: Wed, 11 Feb 2026 16:13:07 GMT
• Title: Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
• Authors: Serra Korkmaz, Adam Izdebski, Jonathan Pirnay, Rasmus Møller-Larsen, Michal Kmicikiewicz, Pankhil Gawade, Dominik G. Grimm, Ewa Szczurek,
• Abstract summary: Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds.<n>We introduce Joint Self-Improvement, which benefits from a joint generative-predictive model and a self-improving sampling scheme.<n>Joint Self-Improvement outperforms state-of-the-art methods under limited evaluation budgets.
• Score: 0.878320610914317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, such candidates are rare and expensive to evaluate, yielding sample efficiency essential. Additionally, surrogate models introduced to predict molecule evaluations, suffer from distribution shift as optimization drives candidates increasingly out-of-distribution. To address these challenges, we introduce Joint Self-Improvement, which benefits from (i) a joint generative-predictive model and (ii) a self-improving sampling scheme. The former aligns the generator with the surrogate, alleviating distribution shift, while the latter biases the generative part of the joint model using the predictive one to efficiently generate optimized molecules at inference-time. Experiments across offline and online molecular optimization benchmarks demonstrate that Joint Self-Improvement outperforms state-of-the-art methods under limited evaluation budgets.

Related papers

• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design [58.8094854658848]
  We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design.<n>We propose an iterative distillation-based fine-tuning framework that enables diffusion models to optimize for arbitrary reward functions.<n>Our off-policy formulation, combined with KL divergence minimization, enhances training stability and sample efficiency compared to existing RL-based methods.
  arXiv  Detail & Related papers  (2025-07-01T05:55:28Z)
• Synergistic Benefits of Joint Molecule Generation and Property Prediction [6.865957689890204]
  Hyformer is a transformer-based joint model that blends the generative and predictive functionalities.<n>We show that Hyformer is simultaneously optimized for molecule generation and property prediction.<n>We also demonstrate the benefits of joint learning in a drug design use case of discovering novel antimicrobialpeptides.
  arXiv  Detail & Related papers  (2025-04-23T09:36:46Z)
• Efficient Generation of Molecular Clusters with Dual-Scale Equivariant Flow Matching [5.909830898977327]
  We develop a dual-scale flow matching method that separates training and inference into coarse-grained and all-atom stages. We demonstrate the effectiveness of this method on a dataset of Y6 molecular clusters obtained through MD simulations.
  arXiv  Detail & Related papers  (2024-10-10T02:17:27Z)
• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
  AliDiff is a novel framework to align pretrained target diffusion models with preferred functional properties. It can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score.
  arXiv  Detail & Related papers  (2024-07-01T06:10:29Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• Optimal Budgeted Rejection Sampling for Generative Models [54.050498411883495]
  Rejection sampling methods have been proposed to improve the performance of discriminator-based generative models. We first propose an Optimal Budgeted Rejection Sampling scheme that is provably optimal. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance.
  arXiv  Detail & Related papers  (2023-11-01T11:52:41Z)
• Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
  We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-30T06:10:22Z)
• Controlled Molecule Generator for Optimizing Multiple Chemical Properties [9.10095508718581]
  We propose a new optimized molecule generator model based on the Transformer with two constraint networks. Experiments demonstrate that our proposed model outperforms state-of-the-art models by a significant margin for optimizing multiple properties simultaneously.
  arXiv  Detail & Related papers  (2020-10-26T21:26:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.