检索结果-内蒙古大学图书馆

9th IEEE International Conference on Big Data (IEEE BigData)

作者： Li, Jiamu Zhang, Ji Wang, Jian Zhu, Youwen Bah, Mohamed Jaward Yang, Gaoming Gan, Yuquan Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China Univ Southern Queensland Toowoomba Qld Australia Zhejiang Lab Hangzhou Peoples R China Anhui Univ Sci & Technol Huainan Peoples R China Xian Univ Posts & Telecommun Xian Peoples R China

ISBN: (纸本)9781665439022

The curse of dimensionality in high-dimensional data makes it difficult to capture the abnormality of data points in full data space. To deal with this problem, we propose an outlier detection model based on variational autoencoder and Genetic Algorithm for subspace outlier analysis of high-dimensional data (VAGA). The proposed VAGA model constructs a variational autoencoder (VAE) to preliminarily detect outliers. Then the genetic algorithm (GA) is used to search the abnormal subspace of the outliers obtained by the VAE layer to provide a basis for subspace outlier analysis. The subsequent clustering of the abnormal subspaces help filter out the false positives which are fed back to the VAE layer to adjust network weights. The comparative experiments performed on three public benchmark datasets show that the outlier detection results of the proposed VAGA model are highly interpretable and have better accuracy performance than the state-of-the-art outlier detection methods.

关键词： outlier detection variational autoencoder genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

variational DIALOGUE GENERATION WITH NORMALIZING FLOWS

VARIATIONAL DIALOGUE GENERATION WITH NORMALIZING FLOWS

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Luo, Tien-Ching Chien, Jen-Tzung Natl Chiao Tung Univ Dept Elect & Comp Engn Hsinchu Taiwan

ISBN: (纸本)9781728176055

Conditional variational autoencoder (cVAE) has shown promising performance in dialogue generation. However, there still exists two issues in dialog cVAE model. The first issue is the Kullback-Leiblier (KL) vanishing problem which results in degenerating cVAE into a simple recurrent neural network. The second issue is the assumption of isotropic Gaussian prior for latent variable which is too simple to assure diversity of the generated responses. To handle these issues, a simple distribution should be transformed into a complex distribution and simultaneously the value of KL divergence should be preserved. This paper presents the dialogue flow VAE (DF-VAE) for variational dialogue generation. In particular, KL vanishing is tackled by a new normalizing flow. An inverse autoregressive flow is proposed to transform isotropic Gaussian prior to a rich distribution. In the experiments, the proposed DF-VAE is significantly better than the other methods in terms of different evaluation metrics. The diversity of generated dialogue responses is enhanced. Ablation study is conducted to illustrate the merit of the proposed flow models.

关键词： Dialogue generation recurrent neural network variational autoencoder normalizing flow

来源：评论

学校读者我要写书评

暂无评论

Learning Disentangled User Representation Based on Controllable VAE for Recommendation 26th

Learning Disentangled User Representation Based on Controlla...

引用

26th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Li, Yunyi Zhao, Pengpeng Wang, Deqing Xian, Xuefeng Liu, Yanchi Sheng, Victor S. Soochow Univ Inst Artificial Intelligence Sch Comp Sci & Technol Suzhou Peoples R China Beihang Univ Suzhou Peoples R China Suzhou Vocat Univ Suzhou Peoples R China NEC Labs Amer Princeton NJ USA Texas Tech Univ Dept Comp Sci Lubbock TX USA

ISBN: (纸本)9783030731991;9783030732004

User behaviour on purchasing is always driven by complex latent factors, which are highly disentangled in the real world. Learning latent factorized representation of users can uncover user intentions behind the observed data (i.e. user-item interaction) and improve the robustness and interpretability of the recommender system. However, existing collaborative filtering methods learning disentangled representation face problems of balancing the trade-off between reconstruction quality and disentanglement. In this paper, we propose a controllable variational autoencoder framework for collaborative filtering. Specifically, we adopt a modified Proportional-Integral-Derivative (PID) control to the beta-VAE objective to automatically tune the hyperparameter beta using the output of Kullback-Leibler divergence as feedback. We further introduce item embeddings to guide the system to learn representation related to the real-world concepts using a factorized Gaussian distribution. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines. We further evaluate our model's effectiveness to control the trade-off between reconstruction error and disentanglement quality in the recommendation.

关键词： variational autoencoder Disentangled representation learning Recommender system

来源：评论

学校读者我要写书评

暂无评论

Vector-Quantized autoencoder With Copula for Collaborative Filtering 21

Vector-Quantized Autoencoder With Copula for Collaborative F...

引用

30th ACM International Conference on Information and Knowledge Management (CIKM)

作者： Wang, Guanyu Zhong, Ting Xu, Xovee Zhang, Kunpeng Zhou, Fan Wang, Yong Univ Elect Sci & Technol China Chengdu Peoples R China Univ Maryland College Pk MD USA Zhengzhou Aiwen Comp Technol Co Ltd Zhengzhou Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (纸本)9781450384469

In theory, the variational auto-encoder (VAE) is not suitable for recommendation tasks, although it has been successfully utilized for collaborative filtering (CF) models. In this paper, we propose a Gaussian Copula-Vector Quantized autoencoder (GC-VQAE) model that differs prior arts in two key ways: (1) Gaussian Copula helps to model the dependencies among latent variables which are used to construct a more complex distribution compared with the meanfield theory;and (2) by incorporating a vector quantisation method into encoders our model can learn discrete representations which are consistent with the observed data rather than directly sampling from the simple Gaussian distributions. Our approach is able to circumvent the "posterior collapse" issue and break the prior constraint to improve the flexibility of latent vector encoding and learning ability. Empirically, GC-VQAE can significantly improve the recommendation performance compared to existing state-of-the-art methods.

关键词： Recommender system vector quantisation Gaussian Copula collaborative filtering variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

LEVERAGING 3D INFORMATION IN UNSUPERVISED BRAIN MRI SEGMENTATION 18

LEVERAGING 3D INFORMATION IN UNSUPERVISED BRAIN MRI SEGMENTA...

引用

18th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Lambert, Benjamin Louis, Maxime Doyle, Senan Forbes, Florence Dojat, Michel Tucholka, Alan Pixyl Res & Dev Lab F-38000 Grenoble France Univ Grenoble Alpes INRIA CNRS Grenoble INPLJK F-38000 Grenoble France Univ Grenoble Alpes INSERM U1216 Grenoble Inst Neurosci F-38000 Grenoble France

ISBN: (纸本)9781665412469

Automatic segmentation of brain abnormalities is challenging, as they vary considerably from one pathology to another. Current methods are supervised and require numerous annotated images for each pathology, a strenuous task. To tackle anatomical variability, Unsupervised Anomaly Detection (UAD) methods are proposed, detecting anomalies as outliers of a healthy model learned using a variational autoencoder (VAE). Previous work on UAD adopted 2D approaches, meaning that MRIs are processed as a collection of independent slices. Yet, it does not fully exploit the spatial information contained in MRI. Here, we propose to perform UAD in a 3D fashion and compare 2D and 3D VAEs. As a side contribution, we present a new loss function guarantying a robust training. Learning is performed using a multicentric dataset of healthy brain MRIs, and segmentation performances are estimated on White-Matter Hyperintensities and tumors lesions. Experiments demonstrate the interest of 3D methods which outperform their 2D counterparts.

关键词： Deep Learning variational autoencoder Anomaly Detection Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

引用

MACHINE LEARNING WITH APPLICATIONS 2023年 13卷

作者： Alanazi, Yasir Schram, Malachi Rajput, Kishansingh Goldenberg, Steven Vidyaratne, Lasitha Pappas, Chris Radaideh, Majdi I. Lu, Dan Ramuhalli, Pradeep Cousineau, Sarah Thomas Jefferson Natl Accelerator Facil Newport News VA 23606 USA Oak Ridge Natl Lab Oak Ridge TN 37830 USA Univ Michigan Dept Nucl Engn & Radiol Sci Ann Arbor MI 48109 USA

We present a multi-module framework based on Conditional variational autoencoder (CVAE) to detect anomalies in the power signals coming from multiple High Voltage Converter Modulators (HVCMs). We condition the model with the specific modulator type to capture different representations of the normal waveforms and to improve the sensitivity of the model to identify a specific type of fault when we have limited samples for a given module type. We studied several Artificial Neural Network (ANN) architectures for our CVAE model and evaluated the model performance by looking at their loss landscape for stability and generalization. Our results for the Spallation Neutron Source (SNS) experimental data show that the trained model generalizes well to detecting multiple fault types for several HVCM module types. The results of this study can be used to improve the HVCM reliability and overall SNS uptime.

关键词： Anomaly detection variational autoencoder Spallation Neutron Source Accelerators High Voltage Converter Modulator

来源：评论

学校读者我要写书评

暂无评论

Enhancing Long Term Fairness in Recommendations with variational autoencoders 11

Enhancing Long Term Fairness in Recommendations with Variati...

引用

11th International Conference on Management of Digital EcoSystems (MEDES)

作者： Borges, Rodrigo Stefanidis, Kostas Univ Sao Paulo Sao Paulo Brazil Tampere Univ Tampere Finland

ISBN: (纸本)9781450362382

Recommender systems have become indispensable for several Web sites, helping users deal with big amounts of data. They are capable of analyzing user/item interactions taking place on-line, and provide each user with a list of suggestions sorted by relevance. Items with the same or very close relevance, however, may occupy different positions in the ranking and may be exposed to completely different levels of attention. This promotes unfair treatment and can only be addressed by a long term strategy. variational autoencoders (VAEs) were recently proposed as the state-of-the-art for collaborative filtering recommendations, but as every other approach, they generate homogeneous prediction scores among the highest positions. In this paper, we propose incorporating randomness in the regular operation of VAEs in order to increase the fairness (mitigate the position bias) in multiple rounds of recommendation. We argue that adding a noise component when sampling values from VAE's latent representation provides long term fairness, despite of a tolerable decrease in ranking quality (NDCG). We calculate the trade-off between unfairness and NDCG when introducing 4 different noise distributions. The solution has proved to be a very practical one and the results point for a clear positive effect of turning recommendation far more fair, despite some small NDCG loss in Movie Lens, Netflix and MSD datasets. In our best scenario, the unfairness was reduced by 76% despite a decrease of 5% in the quality of ranking.

关键词： Fairness in Ranking variational autoencoder Collaborative Filtering Recommendation Systems Position Bias

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Techniques for Island Heightmap Generation

Comparative Analysis of Machine Learning Techniques for Isla...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Demergis, Dimitri Rowan Univ Coll Sci & Math Glassboro NJ 08028 USA

ISBN: (纸本)9780738133669

Traditional approaches to terrain heightmap generation rely on geometric methods to generate a matrix of elevation values using noise functions. More advanced approaches attempt to model the natural processes that shape landmasses in the real world, such as wind, moisture, and rainfall. This survey leverages recent advancements in image generation using generative machine learning models in order to evaluate their effectiveness in this problem space. A variational autoencoder (VAE), generative adversarial network (GAN), and PixelCNN network are trained on real-world island heightmap data and produce realistic island terrain. The author compares the results in terms of image quality and "closeness" to the original real images, and evaluates the trade-off between quality and training/generation speed.

关键词： machine learning generative models deep learning variational autoencoder generative adversarial network PixelCNN PixelRNN terrain generation landscape generation heightmap image synthesis

来源：评论

学校读者我要写书评

暂无评论

Detection of Abnormal Folding Patterns with Unsupervised Deep Generative Models 4th

Detection of Abnormal Folding Patterns with Unsupervised Dee...

引用

4th International Workshop on Machine Learning in Clinical Neuroimaging (MLCN)

作者： Guillon, Louise Cagna, Bastien Dufumier, Benoit Chavas, Joel Riviere, Denis Mangin, Jean-Francois Univ Paris Saclay CEA CNRS NeuroSpinBaobab Gif Sur Yvette France IPParis Telecom Paris LTCI Palaiseau France

ISBN: (纸本)9783030875862;9783030875855

Although the main structures of cortical folding are present in each human brain, the folding pattern is unique to each individual. Because of this large normal variability, the identification of abnormal patterns associated to developmental disorders is a complex open challenge. In this paper, we tackle this problem as an anomaly detection task and explore the potential of deep generative models using benchmarks made up of synthetic anomalies. To focus learning on the folding geometry, brain MRI are preprocessed first to deal only with a skeleton-based negative cast of the cortex. A variational auto-encoder is trained to get a representation of the regional variability of the folding pattern of the general population. Then several synthetic benchmark datasets of abnormalities are designed. The latent space expressivity is assessed through classification experiments between control's and abnormal's latent codes. Finally, the properties encoded in the latent space are analyzed through perturbation of specific latent dimensions and observation of the resulting modification of the reconstructed images. The results have shown that the latent representation is rich enough to distinguish subtle differences like asymmetries between the right and left hemispheres.

关键词： variational autoencoder Brain architecture Cortical folding Anomaly benchmark Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Narrowing of VAE Bottlenecks Using GECO and L₀ Regularization

Dynamic Narrowing of VAE Bottlenecks Using GECO and <i>L</i>...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： De Boom, Cedric Wauthier, Samuel Verbelen, Tim Dhoedt, Bart Univ Ghent IDLab Dept Informat Technol IMEC Technologiepk Zwijnaarde 126 B-9052 Ghent Belgium

ISBN: (纸本)9780738133669

When designing variational autoencoders (VAEs) or other types of latent space models, the dimensionality of the latent space is typically defined upfront. In this process, it is possible that the number of dimensions is under- or overprovisioned for the application at hand. In case the dimensionality is not predefined, this parameter is usually determined using time- and resource-consuming cross-validation. For these reasons we have developed a technique to shrink the latent space dimensionality of VAEs automatically and on-the-fly during training using Generalized ELBO with Constrained Optimization (GECO) and the L-0-Augment-REINFORCE-Merge (L-0-ARM) gradient estimator. The GECO optimizer ensures that we are not violating a predefined upper bound on the reconstruction error. This paper presents the algorithmic details of our method along with experimental results on five different datasets. We find that our training procedure is stable and that the latent space can be pruned effectively without violating the GECO constraints.

关键词： variational autoencoder VAE latent space reduction GECO L-0 regularization ARM

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：