In recent years, deep generative models have been successfully adopted for various molecular design tasks, particularly in the life and material sciences. A critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks aimed at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task is impractical. Furthermore, the black-box nature of typical downstream tasks$\unicode{x2013}$such as property prediction$\unicode{x2013}$makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose a novel approach for a model uncertainty-guided fine-tuning of a pre-trained variational autoencoder (VAE)-based GMD model through performance feedback in an active learning setting. The main idea is to quantify model uncertainty in the generative model, which is made efficient by working within a low-dimensional active subspace of the high-dimensional VAE parameters explaining most of the variability in the model's output. The inclusion of model uncertainty expands the space of viable molecules through decoder diversity. We then explore the resulting model uncertainty class via black-box optimization made tractable by low-dimensionality of the active subspace. This enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties, using multiple VAE-based generative models, demonstrate that our uncertainty-guided fine-tuning approach consistently outperforms the original pre-trained models.
Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation
Barcelona Supercomputing Center (BSC)（巴塞罗那超级计算中心）；PhD program in Biotechnology, Faculty of Pharmacy and Food Sciences, University of Barcelona (UB)（巴塞罗那大学药学与食品科学系生物技术博士项目）；Alzheimer's Research UK Oxford Drug Discovery Institute, Centre for Medicines Discovery, Nuffield Department of Medicine, Oxford, UK（英国阿尔茨海默病研究奥德赛药物发现研究所、药物发现中心、医学系，牛津，英国）；Centre for Medicines Discovery, Nuffield Department of Medicine Research Building (NDMRB), University of Oxford, Oxford, UK（药物发现中心、医学系研究大楼（NDMRB）、牛津大学，牛津，英国）
Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
Department of Statistics（统计学系）；Department of Computer Science（计算机科学系）；Neuroscience Center（神经科学中心）；Neuroscience Center and Department of Psychology（神经科学中心和心理学系）；Department of Psychology（心理学系）
A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets
Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
LMU Munich（慕尼黑大学）；University of Georgia（佐治亚大学）；Northwestern University（西北大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；The Hong Kong Polytechnic University（香港理工大学）
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
School of Computer Science, Wuhan University（武汉大学计算机学院）；JD Explore Academy, JD.com（京东探索研究院）；School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院）；School of Computer Science, Yunnan University（云南大学计算机学院）；School of Computing, Macquarie University（麦考瑞大学计算学院）
Enhancing the conformal predictability of context-aware recommendation systems by using Deep Autoencoders
Faculty of Science of Tunis, University of Tunis El-Manar（突尼斯大学理工学院）；SVKM’s Dwarkadas J. Sanghvi College of Engineering（SVKM德瓦尔卡斯贾亚甘吉学院）；The Maersk Mc-Kinney Moller Institute, University of Southern Denmark（马士基麦金尼莫勒研究所，南部丹麦大学）；Department of Software Science, Tallinn University of Technology（塔林技术大学软件科学系）
MOLA: Enhancing Industrial Process Monitoring Using Multi-Block Orthogonal Long Short-Term Memory Autoencoder
School of Chemical Engineering, Oklahoma State University（俄克拉荷马州立大学化学工程学院）；College of Chemical Engineering, Beijing University of Chemical Technology（北京化工大学化学工程学院）；Cain Department of Chemical Engineering, Louisiana State University（路易斯安那州立大学化学工程Cain学院）
LSTM Autoencoder-based Deep Neural Networks for Barley Genotype-to-Phenotype Prediction
School of Information Technology, Murdoch University（默多克大学信息技术学院）；School of Medical, Molecular and Forensic Sciences, Murdoch University（默多克大学医学、分子与法医学学院）；Western Crop Genetics Alliance, Murdoch University（默多克大学西部作物遗传学联盟）；Western Australian State Agricultural Biotechnology Centre（西澳大利亚州农业生物技术中心）；Department of Primary Industries and Regional Development（初级产业与区域发展部）
Enhancing Diagnostic Accuracy for Urinary Tract Disease through Explainable SHAP-Guided Feature Selection and Classification
Labcin - Nature Inspired Computing Laboratory（Labcin - 自然启发计算实验室）；Federal University of Espírito Santo（巴西圣埃斯皮里图联邦大学）；Graduate Program in Computer Science（计算机科学研究生项目）
