相关论文
2017 - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

Abstract. Time series data in practical applications always contain missing values due to sensor malfunction, network failure, outliers etc. In order to handle missing values in time series, as well as the lack of considering temporal properties in machine learning models, we propose a spatiotemporal prediction framework based on missing value processing algorithms and deep recurrent neural network (DRNN). By using missing tag and missing interval to represent time series patterns, we implement three different missing value fixing algorithms, which are further incorporated into deep neural network that consists of LSTM (Long Short-term Memory) layers and fully connected layers. Real-world air quality and meteorological datasets (Jingjinji area, China) are used for model training and testing. Deep feed forward neural networks (DFNN) and gradient boosting decision trees (GBDT) are trained as baseline models against the proposed DRNN. Performances of three missing value fixing algorithms, as well as different machine learning models are evaluated and analysed. Experiments show that the proposed DRNN framework outperforms both DFNN and GBDT, therefore validating the capacity of the proposed framework. Our results also provides useful insights for better understanding of different strategies that handle missing values.

2009 - SIAM J. Appl. Dyn. Syst.
Dynamical State and Parameter Estimation

We discuss the problem of determining unknown fixed parameters and unobserved state variables in nonlinear models of a dynamical system using observed time series data from that system. In dynamical terms this requires synchronization of the experimental data with time series output from a model. If the model and the experimental system are chaotic, the synchronization manifold, where the data time series is equal to the model time series, may be unstable. If this occurs, then small perturbations in parameters or state variables can lead to large excursions near the synchronization manifold and produce a very complex surface in any estimation metric for those quantities. Coupling the experimental information to the model dynamics can lead to a stabilization of this manifold by reducing a positive conditional Lyapunov exponent (CLE) to a negative value. An approach called dynamical parameter estimation (DPE) addresses these instabilities and regularizes them, allowing for smooth surfaces in the space of pa...

2002 - ECAI
Multiple and Partial Periodicity Mining in Time Series Databases

Periodicity search in time series is a problem that has been investigated by mathematicians in various areas, such as statistics, economics, and digital signal processing. For large databases of time series data, scalability becomes an issue that traditional techniques fail to address. In existing time series mining algorithms for detecting periodic patterns, the period length is user-specified. This is a drawback especially for datasets where no period length is known in advance. We propose an algorithm that extracts a set of candidate periods featured in a time series that satisfy a minimum confidence threshold, by utilizing the autocorrelation function and FFT as a filter. We provide some mathematical background as well as experimental results.

2015 - BMC Bioinformatics
SW1PerS: Sliding windows and 1-persistence scoring; discovering periodicity in gene expression time series data

BackgroundIdentifying periodically expressed genes across different processes (e.g. the cell and metabolic cycles, circadian rhythms, etc) is a central problem in computational biology. Biological time series may contain (multiple) unknown signal shapes of systemic relevance, imperfections like noise, damping, and trending, or limited sampling density. While there exist methods for detecting periodicity, their design biases (e.g. toward a specific signal shape) can limit their applicability in one or more of these situations.MethodsWe present in this paper a novel method, SW1PerS, for quantifying periodicity in time series in a shape-agnostic manner and with resistance to damping. The measurement is performed directly, without presupposing a particular pattern, by evaluating the circularity of a high-dimensional representation of the signal. SW1PerS is compared to other algorithms using synthetic data and performance is quantified under varying noise models, noise levels, sampling densities, and signal shapes. Results on biological data are also analyzed and compared.ResultsOn the task of periodic/not-periodic classification, using synthetic data, SW1PerS outperforms all other algorithms in the low-noise regime. SW1PerS is shown to be the most shape-agnostic of the evaluated methods, and the only one to consistently classify damped signals as highly periodic. On biological data, and for several experiments, the lists of top 10% genes ranked with SW1PerS recover up to 67% of those generated with other popular algorithms. Moreover, the list of genes from data on the Yeast metabolic cycle which are highly-ranked only by SW1PerS, contains evidently non-cosine patterns (e.g. ECM33, CDC9, SAM1,2 and MSH6) with highly periodic expression profiles. In data from the Yeast cell cycle SW1PerS identifies genes not preferred by other algorithms, hence not previously reported as periodic, but found in other experiments such as the universal growth rate response of Slavov. These genes are BOP3, CDC10, YIL108W, YER034W, MLP1, PAC2 and RTT101.ConclusionsIn biological systems with low noise, i.e. where periodic signals with interesting shapes are more likely to occur, SW1PerS can be used as a powerful tool in exploratory analyses. Indeed, by having an initial set of periodic genes with a rich variety of signal types, pattern/shape information can be included in the study of systems and the generation of hypotheses regarding the structure of gene regulatory networks.

2001 - Physical Review Letters
Surrogate Test for Pseudoperiodic Time Series Data

For time series exhibiting strong periodicities, standard (linear) surrogate methods are not useful. We describe a new algorithm that can test against the null hypothesis of a periodic orbit with uncorrelated noise. We demonstrate the application of this method to artificial data and experimental time series, including human electrocardiogram recordings during sinus rhythm and ventricular tachycardia.

2007 - Knowledge and Information Systems
Automatic outlier detection for time series: an application to sensor data

In this article we consider the problem of detecting unusual values or outliers from time series data where the process by which the data are created is difficult to model. The main consideration is the fact that data closer in time are more correlated to each other than those farther apart. We propose two variations of a method that uses the median from a neighborhood of a data point and a threshold value to compare the difference between the median and the observed data value. Both variations of the method are fast and can be used for data streams that occur in quick succession such as sensor data on an airplane.

2020 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
A U-Net Based Discriminator for Generative Adversarial Networks

Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images. To target this issue we propose an alternative U-Net based discriminator architecture, borrowing the insights from the segmentation literature. The proposed U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images, by providing the global image feedback as well. Empowered by the per-pixel response of the discriminator, we further propose a per-pixel consistency regularization technique based on the CutMix data augmentation, encouraging the U-Net discriminator to focus more on semantic and structural changes between real and fake images. This improves the U-Net discriminator training, further enhancing the quality of generated samples. The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics, enabling the generator to synthesize images with varying structure, appearance and levels of detail, maintaining global and local realism. Compared to the BigGAN baseline, we achieve an average improvement of 2.7 FID points across FFHQ, CelebA, and the proposed COCO-Animals dataset.

2018 - ArXiv
Is Generator Conditioning Causally Related to GAN Performance?

Recent work (Pennington et al, 2017) suggests that controlling the entire distribution of Jacobian singular values is an important design consideration in deep learning. Motivated by this, we study the distribution of singular values of the Jacobian of the generator in Generative Adversarial Networks (GANs). We find that this Jacobian generally becomes ill-conditioned at the beginning of training. Moreover, we find that the average (with z from p(z)) conditioning of the generator is highly predictive of two other ad-hoc metrics for measuring the 'quality' of trained GANs: the Inception Score and the Frechet Inception Distance (FID). We test the hypothesis that this relationship is causal by proposing a 'regularization' technique (called Jacobian Clamping) that softly penalizes the condition number of the generator Jacobian. Jacobian Clamping improves the mean Inception Score and the mean FID for GANs trained on several datasets. It also greatly reduces inter-run variance of the aforementioned scores, addressing (at least partially) one of the main criticisms of GANs.

2019 - ArXiv
High Fidelity Speech Synthesis with Adversarial Networks

Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators which operate on random windows of different sizes. The discriminators analyse the audio both in terms of general realism, as well as how well the audio corresponds to the utterance that should be pronounced. To measure the performance of GAN-TTS, we employ both subjective human evaluation (MOS - Mean Opinion Score), as well as novel quantitative metrics (Frechet DeepSpeech Distance and Kernel DeepSpeech Distance), which we find to be well correlated with MOS. We show that GAN-TTS is capable of generating high-fidelity speech with naturalness comparable to the state-of-the-art models, and unlike autoregressive models, it is highly parallelisable thanks to an efficient feed-forward generator. Listen to GAN-TTS reading this abstract at this https URL.

2002 - Physical review letters
Comment on "Indispensable finite time corrections for Fokker-Planck equations from time series data".

A Comment on the Letter by Mario Ragwitz and Holger Kantz, Phys. Rev. Lett. 87, 254501 (2001). The authors of the Letter offer a Reply.

2005 - SIGMOD '05
Subsequence matching on structured time series data

Subsequence matching in time series databases is a useful technique, with applications in pattern matching, prediction, and rule discovery. Internal structure within the time series data can be used to improve these tasks, and provide important insight into the problem domain. This paper introduces our research effort in using the internal structure of a time series directly in the matching process. This idea is applied to the problem domain of respiratory motion data in cancer radiation treatment. We propose a comprehensive solution for analysis, clustering, and online prediction of respiratory motion using subsequence similarity matching. In this system, a motion signal is captured in real time as a data stream, and is analyzed immediately for treatment and also saved in a database for future study. A piecewise linear representation of the signal is generated from a finite state model, and is used as a query for subsequence matching. To ensure that the query subsequence is representative, we introduce the concept of subsequence stability, which can be used to dynamically adjust the query subsequence length. To satisfy the special needs of similarity matching over breathing patterns, a new subsequence similarity measure is introduced. This new measure uses a weighted L1 distance function to capture the relative importance of each source stream, amplitude, frequency, and proximity in time. From the subsequence similarity measure, stream and patient similarity can be defined, which are then used for offline and online applications. The matching results are analyzed and applied for motion prediction and correlation discovery. While our system has been customized for use in radiation therapy, our approach to time series modeling is general enough for application domains with structured time series data.

2020 - ArXiv
Consistency Regularization for Generative Adversarial Networks

Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization---a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of the discriminator to these augmentations. We conduct a series of experiments to demonstrate that consistency regularization works effectively with spectral normalization and various GAN architectures, loss functions and optimizer settings. Our method achieves the best FID scores for unconditional image generation compared to other regularization methods on CIFAR-10 and CelebA. Moreover, Our consistency regularized GAN (CR-GAN) improves state-of-the-art FID scores for conditional generation from 14.73 to 11.48 on CIFAR-10 and from 8.73 to 6.66 on ImageNet-2012.

2001 - Computational Statistics & Data Analysis
Data mining on time series: an illustration using fast-food restaurant franchise data

Abstract Given the widespread use of modern information technology, a large number of time series may be collected during normal business operations. We use a fast-food restaurant franchise as a case to illustrate how data mining can be applied to such time series, and help the franchise reap the benefits of such an effort. Time series data mining at both the store level and corporate level are discussed. Box–Jenkins seasonal ARIMA models are employed to analyze and forecast the time series. Instead of a traditional manual approach of Box–Jenkins modeling, an automatic time series modeling procedure is employed to analyze a large number of highly periodic time series. In addition, an automatic outlier detection and adjustment procedure is used for both model estimation and forecasting. The improvement in forecast performance due to outlier adjustment is demonstrated. Adjustment of forecasts based on stored historical estimates of like-events is also discussed. Outlier detection also leads to information that can be used not only for better inventory management and planning, but also to identify potential sales opportunities. To illustrate the feasibility and simplicity of the above automatic procedures for time series data mining, the SCA Statistical System is employed to perform the related analysis.

2018 - IEEE International Conference on Computer Vision
Generative Adversarial Networks for Extreme Learned Image Compression

We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.

2017 - NIPS
MMD GAN: Towards Deeper Understanding of Moment Matching Network

Generative moment matching network (GMMN) is a deep generative model that differs from Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-sample test based on kernel maximum mean discrepancy (MMD). Although some theoretical guarantees of MMD have been studied, the empirical performance of GMMN is still not as competitive as that of GAN on challenging and large benchmark datasets. The computational efficiency of GMMN is also less desirable in comparison with GAN, partially due to its requirement for a rather large batch size during the training. In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN. The new approach combines the key ideas in both GMMN and GAN, hence we name it MMD GAN. The new distance measure in MMD GAN is a meaningful loss that enjoys the advantage of weak topology and can be optimized via gradient descent with relatively small batch sizes. In our evaluation on multiple benchmark datasets, including MNIST, CIFAR- 10, CelebA and LSUN, the performance of MMD-GAN significantly outperforms GMMN, and is competitive with other representative GAN works.

2002 - Industrial & Engineering Chemistry Research
Pattern Matching in Multivariate Time Series Databases Using a Moving-Window Approach

A novel methodology is proposed for matching patterns in time-series databases based on unsupervised learning and multivariate statistical techniques. The new approach provides a preliminary screening of large amounts of historical data in order to generate a candidate pool of similar periods of operation. This much smaller number of records can then be further evaluated by someone familiar with the process. A new distance similarity factor is proposed that complements the standard principal component analysis similarity factor. The two similarity factors and a moving-window approach are used to characterize the degree of similarity between the current period of interest and windows of historical data. A simulation case study has demonstrated that the proposed pattern matching technique can successfully distinguish between 28 operating conditions for a variety of disturbances, faults, and process changes.

2000 - VLDB
Identifying Representative Trends in Massive Time Series Data Sets Using Sketches

Many data stores, including scientific and financial databases, business warehouses and network repositories, contain time series data. Time series data depict trends for an observed value e.g., value of a stock, number of bytes sent on a router interface, etc., as a function of time. Analysis of the trends over different time windows is of great interest. In this paper, we formalize problems of identifying various 'representative' trends in time series data. Informally, an interval of observations in a time series is defined to be a representative trend if its distance from other intervals satisfy certain properties, for suitably defined distance functions between time series intervals. Natural trends of interest such as periodic or average trends are examples of representative trends. We present efficient algorithms for analyzing massive time series data sets for representative trends over arbitrary windows of interest. Our algorithms are highly processor and 10 efficient; they are approximate but provide probabilistic guarantees for the approximations achieved. Our approach for identifying representative trends relies on a dimensionality reduction technique that replaces each interval by a 'sketch' which is a low dimensional vector. We present efficient algorithms to construct such sketches using a pool of select sketches that we precompute using polynomial convolutions. Using such sketches, we can compute representative trends accurately. Finally, we present results of a detailed experimental study of our technique on very large real data sets. Our results show that, compared to approaches that determine representative trends exactly, our approach shows significant performance gains with only a small loss in accuracy.

2020 - ArXiv
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

Generative adversarial networks (GANs) are a hot research topic recently. GANs have been widely studied since 2014, and a large number of algorithms have been proposed. However, there is few comprehensive study explaining the connections among different GANs variants, and how they have evolved. In this paper, we attempt to provide a review on various GANs methods from the perspectives of algorithms, theory, and applications. Firstly, the motivations, mathematical representations, and structure of most GANs algorithms are introduced in details. Furthermore, GANs have been combined with other machine learning algorithms for specific applications, such as semi-supervised learning, transfer learning, and reinforcement learning. This paper compares the commonalities and differences of these GANs methods. Secondly, theoretical issues related to GANs are investigated. Thirdly, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, medical field, and data science are illustrated. Finally, the future open research problems for GANs are pointed out.

2005
SLEX Analysis of Multivariate Nonstationary Time Series

We develop a procedure for analyzing multivariate nonstationary time series using the SLEX library (smooth localized complex exponentials), which is a collection of bases, each basis consisting of waveforms that are orthogonal and time-localized versions of the Fourier complex exponentials. Under the SLEX framework, we build a family of multivariate models that can explicitly characterize the time-varying spectral and coherence properties. Every model has a spectral representation in terms of a unique SLEX basis. Before selecting a model, we first decompose the multivariate time series into nonstationary components with uncorrelated (nonredundant) spectral information. The best SLEX model is selected using the penalized log energy criterion, which we derive in this article to be the Kullback–Leibler distance between a model and the SLEX principal components of the multivariate time series. The model selection criterion takes into account all of the pairwise cross-correlation simultaneously in the multivariate time series. The proposed SLEX analysis gives results that are easy to interpret, because it is an automatic time-dependent generalization of the classical Fourier analysis of stationary time series. Moreover, the SLEX method uses computationally efficient algorithms and hence is able to provide a systematic framework for extracting spectral features from a massive dataset. We illustrate the SLEX analysis with an application to a multichannel brain wave dataset recorded during an epileptic seizure.

2017 - 1710.07035
Generative Adversarial Networks: An Overview

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.

Multivariate Time Series Imputation with Generative Adversarial Networks

Ying Zhang
|
Xiaojie Yuan
|
Jun Xu
|
Yonghong Luo
|
Xiangrui Cai
|
Y. Zhang
|
Jun Xu
|
Xiaojie Yuan
|
Yonghong Luo
|
Xiangrui Cai

Abstract:Multivariate time series usually contain a large number of missing values, which hinders the application of advanced analysis methods on multivariate time series data. Conventional approaches to addressing the challenge of missing values, including mean/zero imputation, case deletion, and matrix factorization-based imputation, are all incapable of modeling the temporal dependencies and the nature of complex distribution in multivariate time series. In this paper, we treat the problem of missing value imputation as data generation. Inspired by the success of Generative Adversarial Networks (GAN) in image generation, we propose to learn the overall distribution of a multivariate time series dataset with GAN, which is further used to generate the missing values for each sample. Different from the image data, the time series data are usually incomplete due to the nature of data recording process. A modified Gate Recurrent Unit is employed in GAN to model the temporal irregularity of the incomplete time series. Experiments on two multivariate time series datasets show that the proposed model outperformed the baselines in terms of accuracy of imputation. Experimental results also showed that a simple model on the imputed data can achieve state-of-the-art results on the prediction tasks, demonstrating the benefits of our model in downstream applications.

参考文献

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  W. Wothke.  Longitudinal and multigroup modeling with missing data. , 2000 .

[3]  Gustavo E. A. P. A. Batista,et al.  An analysis of four missing data treatment methods for supervised learning , 2003, Appl. Artif. Intell..

[4]  D. Edwards.  Data Mining: Concepts, Models, Methods, and Algorithms , 2003 .

[5]  Edgar Acuña,et al.  The Treatment of Missing Values and its Effect on Classifier Accuracy , 2004 .

[6]  Tshilidzi Marwala,et al.  Missing data: A comparison of neural network and expectation maximization techniques , 2007 .

[7]  Patrick E. McKnight.  Missing Data: A Gentle Introduction , 2007 .

[8]  R. Perera.  Research methods journal club: a gentle introduction to imputation of missing values , 2008, Evidence-based medicine.

[9]  Aníbal R. Figueiras-Vidal,et al.  Pattern classification with missing data: a review , 2010, Neural Computing and Applications.

[10]  J. Graham,et al.  Missing data analysis: making it work in the real world. , 2009, Annual review of psychology.

[11]  Leslie S. Smith,et al.  A neural network-based framework for the reconstruction of incomplete data sets , 2010, Neurocomputing.

[12]  Robert Tibshirani,et al.  Spectral Regularization Algorithms for Learning Large Incomplete Matrices , 2010, J. Mach. Learn. Res..

[13]  Wei-Chang Yeh,et al.  Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm , 2011, Appl. Soft Comput..

[14]  G. Moody,et al.  Predicting in-hospital mortality of ICU patients: The PhysioNet/Computing in cardiology challenge 2012 , 2012, 2012 Computing in Cardiology.

[15]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[16]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[17]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[18]  Luis E. Zárate,et al.  A brief review of the main approaches for treatment of missing data , 2014, Intell. Data Anal..

[19]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[20]  Jehanzeb R. Cheema.  A Review of Missing Data Handling Methods in Education Research , 2014 .

[21]  Gari D. Clifford,et al.  Data preprocessing and mortality prediction: The Physionet/CinC 2012 challenge revisited , 2014, Computing in Cardiology 2014.

[22]  Jiri Kaiser,et al.  Dealing with Missing Values in Data , 2014 .

[23]  Trevor J. Hastie,et al.  Matrix completion and low-rank SVD via fast alternating least squares , 2014, J. Mach. Learn. Res..

[24]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[25]  Pedro Abreu,et al.  Missing data imputation on the 5-year survival prediction of breast cancer patients with unknown discrete values , 2015, Comput. Biol. Medicine.

[26]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[27]  Mehran Amiri,et al.  Missing data imputation using fuzzy-rough methods , 2016, Neurocomputing.

[28]  J. Zico Kolter,et al.  Gradient descent GAN optimization is locally stable , 2017, NIPS.

[29]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[30]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[31]  Zhenan Sun,et al.  Recent Progress of Face Image Synthesis , 2017, 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR).

[32]  Yoshua Bengio,et al.  Maximum-Likelihood Augmented Discrete Generative Adversarial Networks , 2017, ArXiv.

[33]  Pinjia He,et al.  Semantically Consistent Image Completion with Fine-grained Details , 2017, ArXiv.

[34]  John E. Hopcroft,et al.  Stacked Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[36]  Ming-Hsuan Yang,et al.  Generative Face Completion , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Sandeep Subramanian,et al.  Adversarial Generation of Natural Language , 2017, Rep4NLP@ACL.

[38]  Eric Horvitz,et al.  Predicting Mortality of Intensive Care Patients via Learning about Hazard , 2017, AAAI.

[39]  Beng Chin Ooi,et al.  Resolving the Bias in Electronic Medical Records , 2017, KDD.

[40]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Kamalika Chaudhuri,et al.  Approximation and Convergence Properties of Generative Adversarial Learning , 2017, NIPS.

[42]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[43]  Andrew M. Dai,et al.  MaskGAN: Better Text Generation via Filling in the ______ , 2018, ICLR.

[44]  Mihaela van der Schaar,et al.  GAIN: Missing Data Imputation using Generative Adversarial Nets , 2018, ICML.

[45]  Alexandros G. Dimakis,et al.  AmbientGAN: Generative models from lossy measurements , 2018, ICLR.

[46]  Yan Liu,et al.  Recurrent Neural Networks for Multivariate Time Series with Missing Values , 2016, Scientific Reports.

引用
Time Series Anomaly Detection for Smart Grids: A Survey
2021 IEEE Electrical Power and Energy Conference (EPEC)
2021
GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing Data
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2020
Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data
ICLR
2020
Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique
ArXiv
2022
Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observation
J. Comput. Phys.
2019
One-dimensional Deep Image Prior for Time Series Inverse Problems
2022 56th Asilomar Conference on Signals, Systems, and Computers
2019
A Two-Block RNN-Based Trajectory Prediction From Incomplete Trajectory
IEEE Access
2022
Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2020
Clairvoyance: A Pipeline Toolkit for Medical Time Series
ICLR
2023
Learning Representations for Incomplete Time Series Clustering
AAAI
2021
Latent ODEs for Irregularly-Sampled Time Series
ArXiv
2019
Recursive Input and State Estimation: a General Framework for Learning from Time Series With Missing Data
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2021
NRTSI: Non-Recurrent Time Series Imputation for Irregularly-sampled Data
ArXiv
2021
Towards Generating Real-World Time Series Data
2021 IEEE International Conference on Data Mining (ICDM)
2021
Time Series Data Imputation: A Survey on Deep Learning Approaches
ArXiv
2020
Mobile communication base station traffic forecast
2021
A Model-Agnostic Method for PMU Data Recovery Using Optimal Singular Value Thresholding
IEEE Transactions on Power Delivery
2021
Iterative Imputation of Missing Data Using Auto-Encoder Dynamics
ICONIP
2020
Can auto-encoders help with filling missing data?
ICLR 2020
2020
Entity Matching from Unstructured and Dissimilar Data Collections: Semantic and Content Distribution Approach
2020