Conditional Loss and Deep Euler Scheme for Time Series Generation

Remlinger, Carl; Mikael, Joseph; Élie, Romuald

doi:10.1609/aaai.v36i7.20782

Cited by 11 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This measure compares the correlations found in multivariate time series of the real dataset to those of the synthetic dataset. Initially, Remlinger et al [50] described it as the "term-by-term mean squared error (MSE) between empirical correlation from reference samples on one side and from generated samples on the other side". However, this is very vague, as it remains unclear which correlation is used, how it is applied, and how the MSE are aggregated.…”

Section: Distribution-level Measuresmentioning

confidence: 99%

“…Marginal metrics. This is a combination of three classical statistics used to roughly compare the marginal distribution of each time step in the real dataset to its counterpart in the synthetic dataset [50]. Namely, these are the average, 95th percentile, and 5th percentile, which we refer to as s 1 , s 2 , s 3 , respectively, below.…”

Section: Length Histogrammentioning

confidence: 99%

“…Quadratic variation. This measure targets the time series generator's ability to reproduce the temporal structure of each channel [50]. Quadratic variation originally comes from the analysis of stochastic processes and can be simplified for time series to It is initially only applicable to individual univariate time series and needs further aggregation to be useful for the dataset-level.…”

Section: Incoming Nearest Neighbor Distance (Innd)mentioning

confidence: 99%

See 2 more Smart Citations

Evaluation is key: a survey on evaluation measures for synthetic time series

Stenger,

Leppich,

Foster

et al. 2024

J Big Data

View full text Add to dashboard Cite

Synthetic data generation describes the process of learning the underlying distribution of a given real dataset in a model, which is, in turn, sampled to produce new data objects still adhering to the original distribution. This approach often finds application where circumstances limit the availability or usability of real-world datasets, for instance, in health care due to privacy concerns. While image synthesis has received much attention in the past, time series are key for many practical (e.g., industrial) applications. To date, numerous different generative models and measures to evaluate time series syntheses have been proposed. However, regarding the defining features of high-quality synthetic time series and how to quantify quality, no consensus has yet been reached among researchers. Hence, we propose a comprehensive survey on evaluation measures for time series generation to assist users in evaluating synthetic time series. For one, we provide brief descriptions or - where applicable - precise definitions. Further, we order the measures in a taxonomy and examine applicability and usage. To assist in the selection of the most appropriate measures, we provide a concise guide for fast lookup. Notably, our findings reveal a lack of a universally accepted approach for an evaluation procedure, including the selection of appropriate measures. We believe this situation hinders progress and may even erode evaluation standards to a “do as you like”-approach to synthetic data evaluation. Therefore, this survey is a preliminary step to advance the field of synthetic data evaluation.

show abstract

Section: Distribution-level Measuresmentioning

confidence: 99%

Section: Length Histogrammentioning

confidence: 99%

Section: Incoming Nearest Neighbor Distance (Innd)mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation is key: a survey on evaluation measures for synthetic time series

Stenger,

Leppich,

Foster

et al. 2024

J Big Data

View full text Add to dashboard Cite

show abstract

“…Since there are various methods to calculate the distance between vectors, the following experiments are conducted to demonstrate the superiority of Manhattan distance. Besides Manhattan distance, Euler distance [55], Minkowski distance [56], Chebyshev distance [57], and cosine similarity [58] are also selected, and the experimental results are shown in Tables 3 and 4, respectively. From Tables 3 and 4, it can be seen that Manhattan distance achieves the optimal Accuracy, Precision, Recall, F1 and classification time on both baseline datasets.…”

Section: F Model Analysis 1) Importance Analysis Of Each Componentmentioning

confidence: 99%

Word-Level and Pinyin-Level Based Chinese Short Text Classification

Sun

Huo

2022

IEEE Access

View full text Add to dashboard Cite

Short text classification is an important branch of Natural Language Processing. Although CNN and RNN have achieved satisfactory results in the text classification tasks, they are difficult to apply to the Chinese short text classification because of the data sparsity and the homophonic typos problems of them. To solve the above problems, word-level and Pinyin-level based Chinese short text classification model is constructed. Since homophones have the same Pinyin, the addition of Pinyin-level features can solve the homophonic typos problem. In addition, due to the introduction of more features, the data sparsity problem of short text can be solved. In order to fully extract the deep hidden features of the short text, a deep learning model based on BiLSTM, Attention and CNN is constructed, and the residual network is used to solve the gradient disappearance problem with the increase of network layers. Additionally, considering that the complex deep learning network structure will increase the text classification time, the Text Center is constructed. When there is a new text input, the text classification task can be quickly realized by calculating the Manhattan distance between the embedding vector of it and the vectors stored in the Text Center. The Accuracy, Precision, Recall and F1 of the proposed model on the simplifyweibo_4_moods dataset are 0.9713, 0.9627, 0.9765 and 0.9696 respectively, and those on the online_shopping_10_cats dataset are 0.9533, 0.9416, 0.9608 and 0.9511 respectively, which are better than that of the baseline method. In addition, the classification time of the proposed model on simplifyweibo_4_moods and online_shopping_10_cats is 0.0042 and 0.0033 respectively, which is far lower than that of the baseline method.

show abstract

“…Indeed, in order to capture the potentially complex dynamics of variables across time, it is not sufficient to learn the time marginals or even the joint distribution without exploiting the sequential structure. An increasing attention has been paid to these methods in the literature and state-of-the-art generative methods for time series are: Time series GAN [27] which combines an unsupervised adversarial loss on real/synthetic data and supervised loss for generating sequential data, Quant GAN [25] with an adversarial generator using temporal convolutional networks, Causal optimal transport COT-GAN [26] with adversarial generator using the adapted Wasserstein distance for processes, Conditional loss Euler generator [20] starting from a diffusion representation time series and minimizing the conditional distance between transition probabilities of real/synthetic samples, Signature embedding of time series [9], [18], [3], and Functional data analysis with neural SDEs [6].…”

Section: Introductionmentioning

confidence: 99%