TSI-Bench: Benchmarking Time Series Imputation
- URL: http://arxiv.org/abs/2406.12747v1
- Date: Tue, 18 Jun 2024 16:07:33 GMT
- Title: TSI-Bench: Benchmarking Time Series Imputation
- Authors: Wenjie Du, Jun Wang, Linglong Qian, Yiyuan Yang, Fanxing Liu, Zepu Wang, Zina Ibrahim, Haoxin Liu, Zhiyuan Zhao, Yingjie Zhou, Wenjia Wang, Kaize Ding, Yuxuan Liang, B. Aditya Prakash, Qingsong Wen,
- Abstract summary: TSI-Bench is a comprehensive benchmark suite for time series imputation utilizing deep learning techniques.
The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms.
TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes.
- Score: 52.27004336123575
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings. Moreover, although many deep learning forecasting algorithms have demonstrated excellent performance, whether their modeling achievements can be transferred to time series imputation tasks remains unexplored. To bridge these gaps, we develop TSI-Bench, the first (to our knowledge) comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms and identification of meaningful insights into the influence of domain-appropriate missingness ratios and patterns on model performance. Furthermore, TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes. Our extensive study across 34,804 experiments, 28 algorithms, and 8 datasets with diverse missingness scenarios demonstrates TSI-Bench's effectiveness in diverse downstream tasks and potential to unlock future directions in time series imputation research and analysis. The source code and experiment logs are available at https://github.com/WenjieDu/AwesomeImputation.
Related papers
- Deep Time Series Models: A Comprehensive Survey and Benchmark [74.28364194333447]
Time series data is of great significance in real-world scenarios.
Recent years have witnessed remarkable breakthroughs in the time series community.
We release Time Series Library (TSLib) as a fair benchmark of deep time series models for diverse analysis tasks.
arXiv Detail & Related papers (2024-07-18T08:31:55Z) - Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation
for Time Series [49.992908221544624]
Time series data often exhibit numerous missing values, which is the time series imputation task.
Previous deep learning methods have been shown to be effective for time series imputation.
We propose a non-generative time series imputation method that produces accurate imputations with inherent uncertainty.
arXiv Detail & Related papers (2023-12-03T05:52:30Z) - Automatic Feature Engineering for Time Series Classification: Evaluation
and Discussion [0.0]
Time Series Classification (TSC) is a crucial and challenging problem in data science and knowledge engineering.
Several tools for extracting unsupervised informative summary statistics, aka features, from time series have been designed in the recent years.
In this article, we propose a simple TSC process to evaluate the potential predictive performance of the feature sets obtained with existing feature engineering tools.
arXiv Detail & Related papers (2023-08-02T10:46:42Z) - Latent Properties of Lifelong Learning Systems [59.50307752165016]
We introduce an algorithm-agnostic explainable surrogate-modeling approach to estimate latent properties of lifelong learning algorithms.
We validate the approach for estimating these properties via experiments on synthetic data.
arXiv Detail & Related papers (2022-07-28T20:58:13Z) - Early Time-Series Classification Algorithms: An Empirical Comparison [59.82930053437851]
Early Time-Series Classification (ETSC) is the task of predicting the class of incoming time-series by observing as few measurements as possible.
We evaluate six existing ETSC algorithms on publicly available data, as well as on two newly introduced datasets.
arXiv Detail & Related papers (2022-03-03T10:43:56Z) - SAITS: Self-Attention-based Imputation for Time Series [6.321652307514677]
SAITS is a novel method based on the self-attention mechanism for missing value imputation in time series.
It learns missing values from a weighted combination of two diagonally-masked self-attention blocks.
Tests show SAITS outperforms state-of-the-art methods on the time-series imputation task efficiently.
arXiv Detail & Related papers (2022-02-17T08:40:42Z) - Temporal Dependencies in Feature Importance for Time Series Predictions [4.082348823209183]
We propose WinIT, a framework for evaluating feature importance in time series prediction settings.
We demonstrate how the solution improves the appropriate attribution of features within time steps.
WinIT achieves 2.47x better performance than FIT and other feature importance methods on real-world clinical MIMIC-mortality task.
arXiv Detail & Related papers (2021-07-29T20:31:03Z) - An Experimental Review on Deep Learning Architectures for Time Series
Forecasting [0.0]
We provide the most extensive deep learning study for time series forecasting.
Among all studied models, the results show that long short-term memory (LSTM) and convolutional networks (CNN) are the best alternatives.
CNNs achieve comparable performance with less variability of results under different parameter configurations, while also being more efficient.
arXiv Detail & Related papers (2021-03-22T17:58:36Z) - Benchmarking Deep Learning Interpretability in Time Series Predictions [41.13847656750174]
Saliency methods are used extensively to highlight the importance of input features in model predictions.
We set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures.
arXiv Detail & Related papers (2020-10-26T22:07:53Z) - A Constraint-Based Algorithm for the Structural Learning of
Continuous-Time Bayesian Networks [70.88503833248159]
We propose the first constraint-based algorithm for learning the structure of continuous-time Bayesian networks.
We discuss the different statistical tests and the underlying hypotheses used by our proposal to establish conditional independence.
arXiv Detail & Related papers (2020-07-07T07:34:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.