Multimodal Variational Autoencoders (VAEs) have been the subject of intense research in the past years as they can integrate multiple modalities into a joint representation and can thus serve as a promising tool for both data classification and generation. Several approaches toward multimodal VAE learning have been proposed so far, their comparison and evaluation have however been rather inconsistent. One reason is that the models differ at the implementation level, another problem is that the datasets commonly used in these cases were not initially designed to evaluate multimodal generative models. This paper addresses both mentioned issues. First, we propose a toolkit for systematic multimodal VAE training and comparison. The toolkit currently comprises 4 existing multimodal VAEs and 6 commonly used benchmark datasets along with instructions on how to easily add a new model or a dataset. Second, we present a disentangled bimodal dataset designed to comprehensively evaluate the joint generation and cross-generation capabilities across multiple difficulty levels. We demonstrate the utility of our dataset by comparing the implemented state-of-the-art models.
Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders
Advanced Light Source, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室先进光源）；Center for Advanced Mathematics for Energy Research Applications, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室能源研究应用高级数学中心）；Molecular Biophysics & Integrated Bioimaging Division, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室分子生物物理学与综合生物成像部）；Berkeley Synchrotron Infrared Structural Biology program, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室伯克利同步辐射红外结构生物学项目）；Materials Sciences Division, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室材料科学部）；McKetta Department of Chemical Engineering, University of Texas（德克萨斯大学麦凯塔化学工程系）
针对X射线散射数据离线探索和实时分析两大挑战，训练领域特定注意力卷积变分自编码器（C-VAE），学习低维表示以捕捉结构变化，并集成到MLExchange平台的Latent Space Explorer中，支持交互式结构探索。
AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
University of Southern California（南加利福尼亚大学）；National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；Westlake University（西湖大学）；Hunan University（湖南大学）
Distinguishing between Normal and Cancer Cells Using Autoencoder Node Saliency
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
基因表达谱已被广泛用于表征细胞对疾病的反应模式。随着数据变得可用，可扩展的学习工具包对于使用深度学习模型来处理大型数据集以模拟复杂的生物过程变得至关重要。我们提出了一个自动编码器来捕获从基因表达谱中恢复的非线性关系。自动编码器是一种使用人工神经网络的非线性降维技术，它学习未标记数据的隐藏表示。我们训练的自动编码器上收集的肿瘤样本从国家癌症研究所基因组数据共享，并获得一个广义和无监督的潜在表示。我们利用专注于HPC的深度学习工具包Livermore Big Artificial神经网络（LBANN）来高效地并行化训练算法，将计算时间从几个小时减少到几分钟。使用经过训练的自动编码器，我们生成了一个小数据集的潜在表示，其中包含各种肿瘤类型的正常细胞和癌细胞对。一种新的措施，称为自动编码器节点显着性（ANS）的介绍，以确定隐藏的节点，最好区分各种对细胞。我们比较我们的最佳分类节点的主成分分析和可视化的t分布随机邻居嵌入的结果。我们证明了自动编码器可以有效地为数据集中的多个学习任务提取不同的基因特征。
Benchmarking Dimensionality Reduction Techniques for Spatial Transcriptomics
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克奎恩特研究所）；Rajiv Gandhi University（拉贾夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）
Nanyang Technological University（南洋理工大学）；University of Cambridge（剑桥大学）；Loyola Marymount University（洛约拉马利蒙特大学）；Mila（米拉人工智能研究所）；University of Montréal（蒙特利尔大学）；National University of Singapore（新加坡国立大学）
Comprehensive Benchmarking of Machine Learning Methods for Risk Prediction Modelling from Large-Scale Survival Data: A UK Biobank Study
King’s College London（伦敦国王学院）；British Heart Foundation Centre of Research Excellence（英国心脏基金会卓越研究中心）；School of Cardiovascular & Metabolic Medicine and Sciences, King’s College London（伦敦国王学院心血管与代谢医学与科学学院）；Institute of Cardiovascular Science, University College London（伦敦大学学院心血管科学研究所）
该研究在 UK Biobank 大规模生存数据上基准测试八种线性至深度学习生存模型，发现 COX-PH 稳健，而复杂模型仅在特定样本与预测矩阵条件下占优。
