Summary of Tsi-bench: Benchmarking Time Series Imputation, by Wenjie Du et al.
TSI-Bench: Benchmarking Time Series Imputation
by Wenjie Du, Jun Wang, Linglong Qian, Yiyuan Yang, Zina Ibrahim, Fanxing Liu, Zepu Wang, Haoxin Liu, Zhiyuan Zhao, Yingjie Zhou, Wenjia Wang, Kaize Ding, Yuxuan Liang, B. Aditya Prakash, Qingsong Wen
First submitted to arxiv on: 18 Jun 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 The paper presents TSI-Bench, a comprehensive benchmark suite for time series imputation using deep learning techniques. The authors highlight the lack of standardized platforms for evaluating imputation performance and explore whether deep learning forecasting algorithms can be transferred to imputation tasks. They develop a pipeline that standardizes experimental settings, enabling fair evaluation and identifying insights into model performance influenced by domain-specific missing rates and patterns. The study includes 34,804 experiments across 28 algorithms, 8 datasets, and diverse missingness scenarios, demonstrating the effectiveness of TSI-Bench in various downstream tasks and unlocking future directions in time series imputation research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Time series analysis relies on effective imputation to preprocess data. A new benchmark platform called TSI-Bench helps researchers compare different imputation algorithms. The authors also look into whether forecasting models can be used for imputation. They designed a way to standardize experiments and test many different approaches. This study shows that TSI-Bench works well in various situations and opens up new possibilities for time series analysis. |
Keywords
» Artificial intelligence » Deep learning » Time series
