We introduce the Kernel-Elastic Autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE is formulated based on two novel loss functions: modified maximum mean discrepancy and weighted reconstruction. KAE addresses the long-standing challenge of achieving valid generation and accurate reconstruction at the same time. KAE achieves remarkable diversity in molecule generation while maintaining near-perfect reconstructions on the independent testing dataset, surpassing previous molecule-generating models. KAE enables conditional generation and allows for decoding based on beam search resulting in state-of-the-art performance in constrained optimizations. Furthermore, KAE can generate molecules conditional to favorable binding affinities in docking applications as confirmed by AutoDock Vina and Glide scores, outperforming all existing candidates from the training dataset. Beyond molecular design, we anticipate KAE could be applied to solve problems by generation in a wide range of applications.
Quasiparticle Interference Kernel Extraction with Variational Autoencoders via Latent Alignment
Department of Computer Science \& \ University of Notre Dame South Bend, IN, USA;Department of Physics \& Astronomy University of Notre Dame South Bend, IN, USA
Variational Autoencoder Kernel Interpretation and Selection for Classification
University of Madeira(马德拉大学);Interactive Technologies Institute(交互技术研究所);Institute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria(拉斯帕尔马斯大学通信技术发展与创新研究所)
Elastic-Net Multiple Kernel Learning: Combining Multiple Data Sources for Prediction
Centre for Artificial Intelligence, Department of Computer Science, University College London, UK(人工智能中心、计算机科学系、伦敦大学学院、英国);Hawkes Institute, University College London, UK(霍克斯研究所、伦敦大学学院、英国);Department of Computer Science, University College London, UK(计算机科学系、伦敦大学学院、英国);GIGA - CRC Human Imaging, University of Liège, Belgium(GIGA- CRC 人类成像、列日大学、比利时)
Learnable Faster Kernel-PCA for Nonlinear Fault Detection: Deep Autoencoder-Based Realization
Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所精密感知与控制研究中心);University of Chinese Academy of Sciences(中国科学院大学)
针对 KPCA 核参数依赖试错且在线计算开销大的问题,提出基于深度自编码器的 DAE-FE/DAE-PCA 可学习快速实现,并在 TE 基准上验证其等价性、检测优势和约百倍在线加速。
Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders
Maxwell Institute for Mathematical Sciences, The University of Edinburgh(爱丁堡大学麦克斯韦数学研究所);Heriot–Watt University(赫瑞瓦特大学);Max Planck Institute for Dynamics of Complex Technical Systems(马克斯·普朗克复杂技术系统动力学研究所);LAAS-CNRS(法国国家科学研究中心自动控制与系统分析实验室);Université de Toulouse(图卢兹大学);School of Mathematical & Computer Sciences, Heriot–Watt University(赫瑞瓦特大学数学与计算机科学学院)
Unsupervised Feature Selection for Tumor Profiles using Autoencoders and Kernel Methods
Universite de Technologie de Troyes(特鲁瓦技术大学);Instituto de Investigacion en Biomedicina de Buenos Aires (IBioBA)—CONICET Partner Institute of the Max Planck Society(布宜诺斯艾利斯生物医学研究所(IBioBA)—马克斯·普朗克学会合作研究所)
The Chinese University of Hong Kong(香港中文大学);Tencent AI Lab(腾讯人工智能实验室);Georgia Institute of Technology(佐治亚理工学院);University of Texas at Arlington(德克萨斯大学阿灵顿分校)
Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
Lamarr Institute for Machine Learning and Artifical Intelligence(拉玛尔机器学习与人工智能研究所);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Department of Computer Science at Paderborn University(帕德博恩大学计算机科学系);Department of Mechanical and Aerospace Engineering Center for Statistics and Machine Learning(机械与航空航天工程系统计与机器学习中心);Princeton University(普林斯顿大学);Department of Computer Science at TU Dortmund University(杜伊斯堡-艾瑟恩理工大学计算机科学系)
A surrogate model for topology optimisation of elastic structures via parametric autoencoders
Laboratori de Càlcul Numèric (LaCàN), ETS de Ingeniería de Caminos, Canales y Puertos, Universitat Politècnica de Catalunya - BarcelonaTech (UPC), Barcelona, Spain(数值计算实验室(LaCàN)、土木、水利与港口工程系、巴塞罗那技术大学(UPC));Centre Internacional de Mètodes Numèrics en Enginyeria (CIMNE), Barcelona, Spain(国际数值方法工程中心(CIMNE))
Leveraging tensor kernels to reduce objective function mismatch in deep clustering
NORCE Norwegian Research Centre(挪威研究中心(NORCE));UiT The Arctic University of Norway(挪威北极大学);University of Copenhagen(哥本哈根大学);Norwegian Computing Center(挪威计算中心)