检索结果-内蒙古大学图书馆

37th IEEE International Conference on Data Engineering (IEEE ICDE)

作者： Takagi, Shun Takahashi, Tsubasa Cao, Yang Yoshikawa, Masatoshi Kyoto Univ Kyoto Japan LINE Corp Toronto ON Canada

ISBN: (纸本)9781728191843

How can we release a massive volume of sensitive data while mitigating privacy risks? Privacy-preserving data synthesis enables the data holder to outsource analytical tasks to an untrusted third party. The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee. However, the existing method cannot adequately handle high dimensional data. In particular, when the input dataset contains a large number of features, the existing techniques require injecting a prohibitive amount of noise to satisfy differential privacy, which results in the outsourced data analysis meaningless. To address the above issue, this paper proposes privacy-preserving phased generative model (P3GM), which is a differentially private generative model for releasing such sensitive data. P3GM employs the two-phase learning process to make it robust against the noise, and to increase learning efficiency (e.g., easy to converge). We give theoretical analyses about the learning complexity and privacy loss in P3GM. We further experimentally evaluate our proposed method and demonstrate that P3GM significantly outperforms existing solutions. Compared with the state-of-the-art methods, our generated samples look fewer noises and closer to the original data in terms of data diversity. Besides, in several data mining tasks with synthesized data, our model outperforms the competitors in terms of accuracy.

关键词： differential privacy variational autoencoder generative model privacy preserving data synthesis

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Techniques Applied to a Preliminary Exploration of Climatic Traits using Meteosat Water Vapor Images

Computational Intelligence Techniques Applied to a Prelimina...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Valdes, Julio J. Pou, Antonio Natl Res Council Canada Digital Technol Res Ctr Ottawa ON Canada Autonomous Univ Madrid Dept Ecol Madrid Spain

ISBN: (纸本)9780738133669

Meteorological satellites are crucial for understanding and forecasting the flow dynamics of the General Atmospheric Circulation System. They produce large amounts of image information whose analysis and interpretation poses numerous challenges. A collection of computational intelligence techniques are used for investigating the structure of a large series of water vapor (WV) band images from ESA Meteosat satellites from 2009-2020. They include the use of the Visual Information Fidelity image quality measure, intrinsic dimensionality, Uniform Manifold Approximation and Projection (with density information) and deep learning (variational autoencoders, convolutional neural networks and transfer learning). The variational autoencoder extracted features that characterize Water Vapor dynamics, distinguished different season patterns, exposed their interrelationships and provided highly effective classification features. Dimensionality reduction was highly instrumental applied to the VAE's latent spaces, and to VIFp image disimilarity analysis in a novel approach applied to major geographical areas. Supervised classification with deep learning and with the XGBoost algorithm on VAE's latent space, produced highly accurate models for predicting seasons. This computational intelligence approach provided insights about atmospheric dynamics as seen from the WV band images and suggested possible weather-teleconnection processes, as well as new ways for finding signs of unusual climate behavior.

关键词： computational intelligence water vapor satellite images VIFp image similarity intrinsic dimension Umap dimensionality reduction variational autoencoder convolutional neural networks transfer learning atmosphere dynamics climate variations

来源：评论

学校读者我要写书评

暂无评论

Fast Multi-Step Critiquing for VAE-based Recommender Systems 21

Fast Multi-Step Critiquing for VAE-based Recommender Systems

引用

15th ACM Conference on Recommender Systems (RECSYS)

作者： Antognini, Diego Faltings, Boi Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781450384582

Recent studies have shown that providing personalized explanations alongside recommendations increases trust and perceived quality. Furthermore, it gives users an opportunity to refine the recommendations by critiquing parts of the explanations. On one hand, current recommender systems model the recommendation, explanation, and critiquing objectives jointly, but this creates an inherent trade-off between their respective performance. On the other hand, although recent latent linear critiquing approaches are built upon an existing recommender system, they suffer from computational inefficiency at inference due to the objective optimized at each conversation's turn. We address these deficiencies with M&Ms-VAE, a novel variational autoencoder for recommendation and explanation that is based on multimodal modeling assumptions. We train the model under a weak supervision scheme to simulate both fully and partially observed variables. Then, we leverage the generalization ability of a trained M&Ms-VAE model to embed the user preference and the critique separately. Our work's most important innovation is our critiquing module, which is built upon and trained in a self-supervised manner with a simple ranking objective. Experiments on four real-world datasets demonstrate that among state-of-the-art models, our system is the first to dominate or match the performance in terms of recommendation, explanation, and multi-step critiquing. Moreover, M&Ms-VAE processes the critiques up to 25.6x faster than the best baselines. Finally, we show that our model infers coherent joint and cross generation, even under weak supervision, thanks to our multimodal-based modeling and training scheme.

关键词： Conversational Recommendation Critiquing variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

MoEVC: A Mixture of Experts Voice Conversion System With Sparse Gating Mechanism for Online Computation Acceleration 12

MoEVC: A Mixture of Experts Voice Conversion System With Spa...

引用

12th International Symposium on Chinese Spoken Language Processing (ISCSLP)

作者： Chang, Yu-Tao Yang, Yuan-Hong Peng, Yu-Huai Wang, Syu-Siang Chi, Tai-Shih Tsao, Yu Wang, Hsin-Min Natl Chiao Tung Univ Dept Elect & Comp Engn Hsinchu Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan Acad Sinica Inst Informat Sci Taipei Taiwan

ISBN: (纸本)9781728169941

Owing to the recent advancements in deep learning technology, the performance of voice conversion (VC) in terms of quality and similarity has significantly improved. However, complex computation is generally required for deep-learning-based VC systems. This can cause a notable latency, which limits the deployment of such VC systems in real-world applications. Therefore, increasing the efficiency of online computing has become an important task. In this study, we propose a novel mixture-of-experts (MoE) based VC system, termed MoEVC. The MoEVC system uses a gating mechanism to assign weights to feature maps to increase VC performance. In addition, applying sparse constraints on the gating mechanism can skip some convolution processes through elimination of redundant feature maps, thereby accelerating online computing. Experimental results show that by using proper sparse constraints, we can effectively reduce the FLOPs (floating-point operations) count by 70%, while improving VC performance in both objective evaluation and human subjective listening tests.

关键词： Voice conversion variational autoencoder non-parallel VC fully convolutional network mixture of experts

来源：评论

学校读者我要写书评

暂无评论

Sage: Practical and Scalable ML-Driven Performance Debugging in Microservices 21

Sage: Practical and Scalable ML-Driven Performance Debugging...

引用

26th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)

作者： Gan, Yu Liang, Mingyu Dev, Sundar Lo, David Delimitrou, Christina Cornell Univ Ithaca NY 14853 USA Google Sunnyvale CA USA

ISBN: (纸本)9781450383172

Cloud applications are increasingly shifting from large monolithic services to complex graphs of loosely-coupled microservices. Despite the advantages of modularity and elasticity microservices offer, they also complicate cluster management and performance debugging, as dependencies between tiers introduce backpressure and cascading QoS violations. Prior work on performance debugging for cloud services either relies on empirical techniques, or uses supervised learning to diagnose the root causes of performance issues, which requires significant application instrumentation, and is difficult to deploy in practice. We present Sage, a machine learning-driven root cause analysis system for interactive cloud microservices that focuses on practicality and scalability. Sage leverages unsupervised ML models to circumvent the overhead of trace labeling, captures the impact of dependencies between microservices to determine the root cause of unpredictable performance online, and applies corrective actions to recover a cloud service's QoS. In experiments on both dedicated local clusters and large clusters on Google Compute Engine we show that Sage consistently achieves over 93% accuracy in correctly identifying the root cause of QoS violations, and improves performance predictability.

关键词： cloud computing microservices performance debugging QoS counterfactual Bayesian network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Global-Local Item Embedding for Temporal Set Prediction 21

Global-Local Item Embedding for Temporal Set Prediction

引用

15th ACM Conference on Recommender Systems (RECSYS)

作者： Jung, Seungjae Park, Young-Jin Jeong, Jisu Kim, Kyung-Min Kim, Hiun Kim, Minkyu Kwak, Hanock NAVER CLOVA Naver R&D Ctr Seongnam Si Gyeonggi Do South Korea NAVER CLOVA Naver R&D Ctr NAVER AI LAB Seongnam Si Gyeonggi Do South Korea NAVER CLOVA NAVER AI LAB Seongnam Si Gyeonggi Do South Korea NAVER CLOVA Seongnam Si Gyeonggi Do South Korea

ISBN: (纸本)9781450384582

Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e.g., personalized purchase prediction of shopping baskets. While most previous techniques have focused on leveraging a user's history, the study of combining it with others' histories remains untapped potential. This paper proposes Global-Local Item Embedding (GLOIE) that learns to utilize the temporal properties of sets across whole users as well as within a user by coining the names as global and local information to distinguish the two temporal patterns. GLOIE uses variational autoencoder (VAE) and dynamic graph-based model to capture global and local information and then applies attention to integrate resulting item embeddings. Additionally, we propose to use Tweedie output for the decoder of VAE as it can easily model zero-inflated and long-tailed distribution, which is more suitable for several real-world data distributions than Gaussian or multinomial counterparts. When evaluated on three public benchmarks, our algorithm consistently outperforms previous state-of-the-art methods in most ranking metrics.

关键词： Temporal Sets Set Prediction Tweedie Distribution variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

3D POINT CLOUD GENERATION USING ADVERSARIAL TRAINING FOR LARGE-SCALE OUTDOOR SCENE

3D POINT CLOUD GENERATION USING ADVERSARIAL TRAINING FOR LAR...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Shinohara, Takayuki Xiu, Haoyi Matsuoka, Masashi Tokyo Inst Technol Dept Architecture & Bldg Engn Yokohama Kanagawa Japan

ISBN: (纸本)9781665403696

Three-dimensional (3D) point clouds are becoming an important part of the geospatial domain. During research on 3D point clouds, deep-learning models have been widely used for the classification and segmentation of 3D point clouds observed by airborne LiDAR. However, most previous studies used discriminative models, whereas few studies used generative models. Specifically, one unsolved problem is the synthesis of large-scale 3D point clouds, such as those observed in outdoor scenes, because of the 3D point clouds' complex geometric structure. In this paper, we propose a generative model for generating large-scale 3D point clouds observed from airborne LiDAR. Generally, because the training process of the famous generative model called generative adversarial network (GAN) is unstable, we combine a variational autoencoder and GAN to generate a suitable 3D point cloud. We experimentally demonstrate that our framework can generate high-density 3D point clouds by using data from the 2018 IEEE GRSS Data Fusion Contest.

关键词： Generative Adversarial Network variational autoencoder Deep Learning Point Clouds Airborne LiDAR

来源：评论

学校读者我要写书评

暂无评论

Gaussian Process Encoders: VAEs with Reliable Latent-Space Uncertainty

Gaussian Process Encoders: VAEs with Reliable Latent-Space U...

引用

21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Butepage, Judith Maystre, Lucas Lalmas, Mounia Spotify Stockholm Sweden

ISBN: (纸本)9783030865207;9783030865191

variational autoencoders are a versatile class of deep latent variable models. They learn expressive latent representations of high dimensional data. However, the latent variance is not a reliable estimate of how uncertain the model is about a given input point. We address this issue by introducing a sparse Gaussian process encoder. The Gaussian process leads to more reliable uncertainty estimates in the latent space. We investigate the implications of replacing the neural network encoder with a Gaussian process in light of recent research. We then demonstrate how the Gaussian Process encoder generates reliable uncertainty estimates while maintaining good likelihood estimates on a range of anomaly detection problems. Finally, we investigate the sensitivity to noise in the training data and show how an appropriate choice of Gaussian process kernel can lead to automatic relevance determination.

关键词： variational autoencoder Uncertainty estimation Anomaly detection Gaussian process

来源：评论

学校读者我要写书评

暂无评论

It's LeVAsa not LevioSA! Latent Encodings for Valence-Arousal Structure Alignment 21

It's LeVAsa not LevioSA! Latent Encodings for Valence-Arousa...

引用

3rd ACM India Joint International Conference on Data Science and Management of Data (CODS-COMAD)

作者： Nath, Surabhi S. Udandarao, Vishaal Shukla, Jainendra IIIT Delhi Delhi India

ISBN: (纸本)9781450388177

In recent years, great strides have been made in the field of affective computing. Several models have been developed to represent and quantify emotions. Two popular ones include (i) categorical models which represent emotions as discrete labels, and (ii) dimensional models which represent emotions in a Valence-Arousal (VA) circumplex domain. However, there is no standard for annotation mapping between the two labelling methods. We build a novel algorithm for mapping categorical and dimensional model labels using annotation transfer across affective facial image datasets. Further, we utilize the transferred annotations to learn rich and interpretable data representations using a variational autoencoder (VAE). We present "LeVAsa", a VAE model that learns implicit structure by aligning the latent space with the VA space. We evaluate the efficacy of LeVAsa by comparing performance with the Vanilla VAE using quantitative and qualitative analysis on two benchmark affective image datasets. Our results reveal that LeVAsa achieves high latent-circumplex alignment which leads to improved downstream categorical emotion prediction. The work also demonstrates the trade-off between degree of alignment and quality of reconstructions.

关键词： Affective computing representation learning variational autoencoder valence arousal circumplex model

来源：评论

学校读者我要写书评

暂无评论

Machine learning methods for generating high dimensional discrete datasets

引用

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY 2022年第2期12卷 e1450-e1450页

作者： Manco, Giuseppe Ritacco, Ettore Rullo, Antonino Sacca, Domenico Serra, Edoardo IICAR CNR Calabria Italy Univ Calabria DIMES Dept I-87036 Calabria Italy Boise State Univ Comp Sci Dept Boise ID 83725 USA

The development of platforms and techniques for emerging Big Data and Machine Learning applications requires the availability of real-life datasets. A possible solution is to synthesize datasets that reflect patterns of real ones using a two-step approach: first, a real dataset X is analyzed to derive relevant patterns Z and, then, to use such patterns for reconstructing a new dataset X ' that preserves the main characteristics of X. This survey explores two possible approaches: (1) Constraint-based generation and (2) probabilistic generative modeling. The former is devised using inverse mining (IFM) techniques, and consists of generating a dataset satisfying given support constraints on the itemsets of an input set, that are typically the frequent ones. By contrast, for the latter approach, recent developments in probabilistic generative modeling (PGM) are explored that model the generation as a sampling process from a parametric distribution, typically encoded as neural network. The two approaches are compared by providing an overview of their instantiations for the case of discrete data and discussing their pros and cons. This article is categorized under: Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Machine Learning Algorithmic Development > Structure Discovery

关键词： constraints-based models data generation generative adversarial networks generative models inverse frequent itemset mining synthetic dataset 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：