Generative Semi-supervised Learning for Multivariate Time Series Imputation

Miao, Xiaoye; Wu, Yangyang; Wang, Jun; Gao, Yunjun; Mao, Xudong; Yin, Jianwei

doi:10.1609/aaai.v35i10.17086

Cited by 84 publications

(41 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are computation speed and convergence issues on large datasets. Miao et al [32] proposed a novel data complementation model SSGAN by combining GAN and BRITS. The model, on the other hand, requires labeled categories in the input temporal data, limiting its applicability to the realworld scenarios.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Attention-Driven Recurrent Imputation for Traffic Speed

Zhang

et al. 2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

In practice, traffic data collection is often warned by missing data due to communication errors, sensor failures, storage loss, among other factors, leading to impaired data collection and hampering the effectiveness of downstream applications. However, existing imputation approaches focus exclusively on estimating the lost value from incomplete observations and ignore historical data. In this paper, we propose a novel neural network model, namely, Attention-Driven Recurrent Imputation Network (ADRIN), to address the problem of missing traffic data. Specifically, in ADRIN, we devise an Imputation-targeted Long Short-Term Memory (LSTM-I) module for filling in missing data. Meanwhile, we consider the periodicity of historical data and design a historical average calculation module in ADRIN. On this basis, we employ the multi-head self-attention mechanism for further extracting latent temporal features from the output of the two modules. ADRIN is capable of modeling both incomplete observation inputs and historical averages independently to estimate the missing values. We conducted comprehensive experiments on three real-world traffic datasets, to demonstrate that ADRIN consistently outperforms other baselines in a variety of scenarios. Furthermore, ablation experiments are conducted on the various modules of the model, and it is concluded that historical data can significantly enhance the imputation effect.

show abstract

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Attention-Driven Recurrent Imputation for Traffic Speed

Zhang

et al. 2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…E 2 GAN is not an end-to-end joint imputation and classification model but still achieved improved performance over BRITS (AUC increased by 0.02) for mortality prediction using a healthcare dataset. In 2021, Miao et al expanded on this work by introducing SSGAN [73], which comprises a generator, a discriminator, and a semi-supervised classifier that iteratively classifies unlabeled time series data and is based on a bidirectional RNN model like BRITS [73]. SSGAN achieved significantly improved imputation performance compared to BRITS and E 2 GAN as measured by RMSE loss.…”

Section: Advanced Approaches For Handling Missing Data (Time Series D...mentioning

confidence: 99%

Systematic Review of Advanced AI Methods for Improving Healthcare Data Quality in Post COVID-19 Era

Isgut

Gloster

Choi

et al. 2023

IEEE Rev. Biomed. Eng.

View full text Add to dashboard Cite

At the beginning of the COVID-19 pandemic, there was significant hype about the potential impact of artificial intelligence (AI) tools in combatting COVID-19 on diagnosis, prognosis, or surveillance. However, AI tools have not yet been widely successful. One of the key reason is the COVID-19 pandemic has demanded faster real-time development of AI-driven clinical and health support tools, including rapid data collection, algorithm development, validation, and deployment. However, there was not enough time for proper data quality control. Learning from the hard lessons in COVID-19, we summarize the important health data quality challenges during COVID-19 pandemic such as lack of data standardization, missing data, tabulation errors, and noise and artifact. Then we conduct a systematic investigation of computational methods that address these issues, including emerging novel advanced AI data quality control methods that achieve better data quality outcomes and, in some cases, simplify or automate the data cleaning process. We hope this article can assist healthcare community to improve health data quality going forward with novel AI development.

show abstract

“…Generative models have been extensively used for time series data mining tasks, such as time series imputation [37,38], time series data generation [39,40,41]. For forecasting tasks, there have been many generative models based on variational inference [16,42] introduced to conditional probability modeling.…”

Section: Generative Model For Time Seriesmentioning

confidence: 99%

Probabilistic Decomposition Transformer for Time Series Forecasting

Tong¹,

Xie²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Time series forecasting is crucial for many fields, such as disaster warning, weather prediction, and energy consumption. The Transformer-based models are considered to have revolutionized the field of sequence modeling. However, the complex temporal patterns of the time series hinder the model from mining reliable temporal dependencies. Furthermore, the autoregressive form of the Transformer introduces cumulative errors in the inference step. In this paper, we propose the probabilistic decomposition Transformer model that combines the Transformer with a conditional generative model, which provides hierarchical and interpretable probabilistic forecasts for intricate time series. The Transformer is employed to learn temporal patterns and implement primary probabilistic forecasts, while the conditional generative model is used to achieve non-autoregressive hierarchical probabilistic forecasts by introducing latent space feature representations. In addition, the conditional generative model reconstructs typical features of the series, such as seasonality and trend terms, from probability distributions in the latent space to enable complex pattern separation and provide interpretable forecasts. Extensive experiments on several datasets demonstrate the effectiveness and robustness of the proposed model, indicating that it compares favorably with the state of the art.

show abstract

Generative Semi-supervised Learning for Multivariate Time Series Imputation

Cited by 84 publications

References 23 publications

Attention-Driven Recurrent Imputation for Traffic Speed

Attention-Driven Recurrent Imputation for Traffic Speed

Systematic Review of Advanced AI Methods for Improving Healthcare Data Quality in Post COVID-19 Era

Probabilistic Decomposition Transformer for Time Series Forecasting

Contact Info

Product

Resources

About