检索结果-内蒙古大学图书馆

Partial Multiple Imputation With variational autoencoders: Tackling Not at Randomness in Healthcare Data

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2022年第8期26卷 4218-4227页

作者： Pereira, Ricardo Cardoso Abreu, Pedro Henriques Rodrigues, Pedro Pereira Univ Coimbra Ctr Informat & Syst Univ Coimbra Dept Informat Engn P-3030290 Coimbra Portugal Univ Porto Fac Med MEDCIDS Ctr Hlth Technol & Serv Res P-4200319 Porto Portugal

Missing data can pose severe consequences in critical contexts, such as clinical research based on routinely collected healthcare data. This issue is usually handled with imputation strategies, but these tend to produce poor and biased results under the Missing Not At Random (MNAR) mechanism. A recent trend that has been showing promising results for MNAR is the use of generative models, particularly variational autoencoders. However, they have a limitation: the imputed values are the result of a single sample, which can be biased. To tackle it, an extension to the variational autoencoder that uses a partial multiple imputation procedure is introduced in this work. The proposed method was compared to 8 state-of-the-art imputation strategies, in an experimental setup with 34 datasets from the medical context, injected with the MNAR mechanism (10% to 80% rates). The results were evaluated through the Mean Absolute Error, with the new method being the overall best in 71% of the datasets, significantly outperforming the remaining ones, particularly for high missing rates. Finally, a case study of a classification task with heart failure data was also conducted, where this method induced improvements in 50% of the classifiers.

关键词： Medical services Task analysis Data models Principal component analysis Neural networks Mathematical models Mice Healthcare data missing data missing not at random partial multiple imputation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Arbitrary conditional inference in variational autoencoders via fast prior network training

引用

MACHINE LEARNING 2022年第7期111卷 2537-2559页

作者： Wu, Ga Domke, Justin Sanner, Scott Univ Toronto Dept Mech & Ind Engn Toronto ON Canada Univ Massachusetts Coll Comp & Informat Sci Amherst MA 01003 USA

variational autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditionally trained VAEs provide an attractive solution. However, to efficiently support arbitrary queries over pre-trained VAEs when the query and evidence are not known in advance, one is generally reduced to MCMC sampling methods that can suffer from long mixing times. In this paper, we propose an idea of efficiently training small conditional prior networks to approximate the latent distribution of the VAE after conditioning on an evidence assignment;this permits generating query samples without retraining the full VAE. We experimentally evaluate three variations of conditional prior networks showing that (i) they can be quickly optimized for different decompositions of evidence and query and (ii) they quantitatively and qualitatively outperform existing state-of-the-art methods for conditional inference in pre-trained VAEs.

关键词： variational autoencoder Conditional inference Prior network

来源：评论

学校读者我要写书评

暂无评论

Towards Data-Driven Volatility Modeling with variational autoencoders 1

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Dierckx, Thomas Davis, Jesse Schoutens, Wim Katholieke Univ Leuven Dept Stat & Risk Leuven Belgium Katholieke Univ Leuven Dept Comp Sci Leuven Belgium

ISBN: (数字)9783031236334

ISBN: (纸本)9783031236327;9783031236334

In this study, we show how S&P 500 Index volatility surfaces can be modeled in a purely data-driven way using variational autoencoders. The approach autonomously learns concepts such as the volatility level, smile, and term structure without leaning on hypotheses from traditional volatility modeling techniques. In addition to introducing notable improvements to an existing variational autoencoder approach for the reconstruction of both complete and incomplete volatility surfaces, we showcase three practical use cases to highlight the relevance of this approach to the financial industry. First, we show how the latent space learned by the variational autoencoder can be used to produce synthetic yet realistic volatility surfaces. Second, we demonstrate how entire sequences of synthetic volatility surfaces can be generated to stress test and analyze an options portfolio. Third and last, we detect anomalous surfaces in our options dataset and pinpoint exactly which subareas are divergent.

关键词： Volatility modeling variational autoencoder Synthetic data Market simulation Anomaly detection Portfolio stress testing

来源：评论

学校读者我要写书评

暂无评论

Pair-variational autoencoders for Linking and Cross-Reconstruction of Characterization Data from Complementary Structural Characterization Techniques

引用

JACS AU 2023年第9期3卷 2510-2521页

作者： Lu, Shizhao Jayaraman, Arthi Univ Delaware Dept Chem & Biomol Engn Newark DE 19716 USA Univ Delaware Dept Mat Sci & Engn Newark DE 19716 USA

In materials research, structural characterization often requires multiple complementary techniques to obtain a holistic morphological view of a synthesized material. Depending on the availability and accessibility of the different characterization techniques (e.g., scattering, microscopy, spectroscopy), each research facility or academic research lab may have access to high-throughput capability in one technique but face limitations (sample preparation, resolution, access time) with other technique(s). Furthermore, one type of structural characterization data may be easier to interpret than another (e.g., microscopy images are easier to interpret than small-angle scattering profiles). Thus, it is useful to have machine learning models that can be trained on paired structural characterization data from multiple techniques (easy and difficult to interpret, fast and slow in data collection or sample preparation) so that the model can generate one set of characterization data from the other. In this paper we demonstrate one such machine learning workflow, Pair-variational autoencoders (PairVAE), that works with data from small-angle X-ray scattering (SAXS) that present information about bulk morphology and images from scanning electron microscopy (SEM) that present two-dimensional local structural information on the sample. Using paired SAXS and SEM data of newly observed block copolymer assembled morphologies [open access data from ], we train our PairVAE. After successful training, we demonstrate that the PairVAE can generate SEM images of the block copolymer morphology when it takes as input that sample's corresponding SAXS 2D pattern and vice versa. This method can be extended to other soft material morphologies as well and serves as a valuable tool for easy interpretation of 2D SAXS patterns as well as an engine for generating ensembles of similar microscopy images to create a database for other downstream calculations of structure-property relationships.

关键词： machine learning material characterization scattering microscopy variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

ENSEMBLE OF UNSUPERVISED LEARNED IMAGE REPRESENTATIONS BASED ON variational autoencoderS FOR LUNG ADENOCARCINOMA SUBTYPE DIFFERENTIATION 20

ENSEMBLE OF UNSUPERVISED LEARNED IMAGE REPRESENTATIONS BASED...

引用

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Cano, Fabian Alvarez-Jimenez, Charlems Romero, Eduardo Cruz-Roa, Angel Univ Nacl Colombia Cim Lab Res Grp Bogota Colombia Univ Llanos GITECX Villavicencio Colombia Univ Llanos Adalab Res Grp Villavicencio Colombia

ISBN: (纸本)9781665473583

Lung adenocarcinoma is a type of non-small cell lung cancer that accounts for about 40% of all lung cancers, which is divided into different molecular and histological subtypes associated with particular prognosis and treatment. Pathologists stratify for diagnosis mainly by its histo-morphological visual features and patterns, which tends to be challenging because of the nature of lung tissue, a mixture of histologically complex patterns and not having a specialized grading system. Here, an unsupervised computational approach based on an ensemble of tissue-specialized variational auto-encoders, which were trained per histopathology subtype, to build an unsupervised embedded tissue-image representation. This representation was used to train a Random Forest classifier of three lung adenocarcinoma histology subtypes (lepidic, papillary and solid), and a 2D-visually interpretable projection from the learned embedded representation. Experimental results achieve an average F-score of 0.72 +/- 0.05 in the test dataset and a well-separated 2D visual mapping of tissue subtypes.

关键词： Digital Pathology Classification Tissue Representation variational autoencoder Lung Adenocarcinoma

来源：评论

学校读者我要写书评

暂无评论

Providing Previously Unseen Users Fair Recommendations Using variational autoencoders 23

Providing Previously Unseen Users Fair Recommendations Using...

引用

17th ACM Conference on Recommender Systems (RecSys)

作者： Vassoy, Bjornar Langseth, Helge Kille, Benjamin Norwegian Univ Sci & Technol Trondheim Trondelag Norway

ISBN: (纸本)9798400702419

An emerging definition of fairness in machine learning requires that models are oblivious to demographic user information, e.g., a user's gender or age should not influence the model. Personalized recommender systems are particularly prone to violating this definition through their explicit user focus and user modelling. Explicit user modelling is also an aspect that makes many recommender systems incapable of providing hitherto unseen users with recommendations. We propose novel approaches for mitigating discrimination in variational autoencoder-based recommender systems by limiting the encoding of demographic information. The approaches are capable of, and evaluated on, providing users that are not represented in the training data with fair recommendations.

关键词： fairness variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Fast and Efficient Speech Enhancement with variational autoencoders 48

Fast and Efficient Speech Enhancement with Variational Autoe...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Sadeghi, Mostafa Serizel, Romain Université de Lorraine Cnrs Inria Loria NancyF-54000 France

ISBN: (纸本)9781728163277

Unsupervised speech enhancement based on variational autoencoders has shown promising performance compared with the commonly used supervised methods. This approach involves the use of a pre-trained deep speech prior along with a parametric noise model, where the noise parameters are learned from the noisy speech signal with an expectation-maximization (EM)-based method. The E-step involves an intractable latent posterior distribution. Existing algorithms to solve this step are either based on computationally heavy Monte Carlo Markov Chain sampling methods and variational inference, or inefficient optimization-based methods. In this paper, we propose a new approach based on Langevin dynamics that generates multiple sequences of samples and comes with a total variation-based regularization to incorporate temporal correlations of latent vectors. Our experiments demonstrate that the developed framework makes an effective compromise between computational efficiency and enhancement quality, and outperforms existing methods. © 2023 IEEE.

关键词： deep generative model Langevin dynamics Speech enhancement variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Synthetic Data Generation via Lipschitz-Regularised variational autoencoders 9

Differentially Private Synthetic Data Generation via Lipschi...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Gros, Benedikt Wunder, Gerhard Freie Universität Department of Computer Science Berlin Germany

ISBN: (纸本)9798350319804

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to approximate complex high-dimensional distributions from data and draw realistic samples from this learned distribution. It is often overlooked though that generative models are prone to memorising many details of individual training records and often generate synthetic data that too closely resembles the underlying sensitive training data, hence violating strong privacy regulations as, e.g., encountered in health care. Differential privacy is the well-known state-of-the-art framework for guaranteeing protection of sensitive individuals' data, allowing aggregate statistics and even machine learning models to be released publicly without compromising privacy. The training mechanisms however often add too much noise during the training process, and thus severely compromise the utility of these private models. Even worse, the tight privacy budgets do not allow for many training epochs so that model quality cannot be properly controlled in practice. In this paper we explore an alternative approach for privately generating data that makes direct use of the inherent stochasticity in generative models, e.g., variational autoencoders. The main idea is to appropriately constrain the continuity modulus of the deep models instead of adding another noise mechanism on top. For this approach, we derive mathematically rigorous privacy guarantees and illustrate its effectiveness with practical experiments. © 2023 IEEE.

关键词： differential privacy Lipschitz regularisation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Digital pathology whole slide image compression with Vector Quantized variational autoencoders

Digital pathology whole slide image compression with Vector ...

引用

Conference on Medical Imaging - Digital and Computational Pathology

作者： Keighley, Jason de Kamps, Marc Wright, Alexander Treanor, Darren Univ Leeds Woodhouse Lane Leeds LS2 9JT W Yorkshire England Leeds Teaching Hosp NHS Trust Great George St Leeds LS1 3EX W Yorkshire England Linkoping Univ Dept Clin Pathol Linkoping Sweden Linkoping Univ Dept Clin & Expt Med Linkoping Sweden Linkoping Univ Ctr Med Image Sci & Visualizat CMIV Linkoping Sweden Univ Leeds LIDA Leeds W Yorkshire England Alan Turing Inst 96 Euston Rd London NW1 2DB England

ISBN: (纸本)9781510660472;9781510660489

Digital pathology Whole Slide Images (WSIs) are large images (similar to 30 GB/slide uncompressed) of high resolution (0.25 microns per pixel), presenting a significant data storage challenge for hospitals wishing to adopt digital pathology. Lossy compression has been adopted by scanner manufacturers to address this issue - we compare lossy Joint Photographic Experts Group (JPEG) compression for WSIs and investigate the Vector Quantised variational autoencoder 2 variant (VQVAE2) as a possible alternative to reduce file size while encoding useful features in the compressed representation. We trained three VQVAE2 models on a Camelyon 2016 subset to the Compression Ratio (CR) of 19.2:1 (CR1), 9.6:1 (CR2) and 4.8:1 (CR3) and tested on a Camelyon 2016 (DS1) subset;University of California (DS2) and Internal Validation Set (DS3). We then compared compression performance to ImageMagick JPEG and JPEG 2000 implementations. Both JPEG and JPEG 2000 compression outperformed the VQVAE2 implementation within the Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) metrics. The trained VQVAE2 models could visually reproduce WSI tissue structure, but used colours from the original training data within the reconstructions on other datasets.

关键词： variational autoencoder Quantisation Compression Pathology Whole Slide Images Digital Pathology

来源：评论

学校读者我要写书评

暂无评论

Addressing Pilot Contamination in Channel Estimation with variational autoencoders

Addressing Pilot Contamination in Channel Estimation with Va...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Kasibovic, Amar Fesl, Benedikt Baur, Michael Utschick, Wolfgang TUM School of Computation Information and Technology Technical University of Munich Munich Germany

ISBN: (纸本)9798350368741

Pilot contamination (PC) is a well-known problem that affects massive multiple-input multiple-output (MIMO) systems. When frequency and pilots are reused between different cells, PC constitutes one of the main bottlenecks of the system's performance. In this paper, we propose a method based on the variational autoencoder (VAE), capable of reducing the impact of PC-related interference during channel estimation (CE). We obtain the first and second-order statistics of the conditionally Gaussian (CG) channels for both the user equipments (UEs) in a cell of interest and those in interfering cells, and we then use these moments to compute conditional linear minimum mean square error estimates. We show that the proposed estimator is capable of exploiting the interferers' additional statistical knowledge, outperforming other classical approaches. Moreover, we highlight how the achievable performance is tied to the chosen setup, making the setup selection crucial in the study of multi-cell CE. © 2025 IEEE.

关键词： channel estimation generative model pilot contamination variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：