Summary of Deep Learning For Multivariate Time Series Imputation: a Survey, by Jun Wang et al.
Deep Learning for Multivariate Time Series Imputation: A Survey
by Jun Wang, Wenjie Du, Yiyuan Yang, Linglong Qian, Wei Cao, Keli Zhang, Wenjia Wang, Yuxuan Liang, Qingsong Wen
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Deep learning-based methods have made significant progress in handling missing data in multivariate time series (MTS) datasets, leveraging complex temporal dependencies and learned data distributions. This survey provides a comprehensive overview of deep learning approaches for MTSI tasks, proposing a novel taxonomy that categorizes existing methods based on imputation uncertainty and neural network architecture. The PyPOTS Ecosystem is highlighted as an integrated and standardized foundation for MTSI research. Key challenges and future research directions are also discussed, providing valuable insights for further research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep learning helps fix missing data in complex time series datasets! This paper surveys the latest methods for doing this, grouping them into two main categories: how uncertain we are about our answers, and what kind of neural networks we use. It also looks at a special toolkit called PyPOTS that makes it easier to do research on this topic. The paper ends by talking about the biggest challenges we still need to solve. |
Keywords
* Artificial intelligence * Deep learning * Neural network * Time series
