Summary of Cats: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series As Exogenous Variables, By Jiecheng Lu et al.
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
by Jiecheng Lu, Xu Han, Yan Sun, Shihao Yang
First submitted to arxiv on: 4 Mar 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 A deep learning-based method for Multivariate Time Series Forecasting (MTSF) is introduced to address the deficiency in current multivariate approaches. Recent univariate models have shown superior performance, but this new approach constructs Auxiliary Time Series (ATS) from Original Time Series (OTS) to capture inter-series relationships. The ATS principle is implemented through modules ensuring continuity, sparsity, and variability. Despite using a basic 2-layer MLP as the core predictor, the proposed method achieves state-of-the-art results with reduced complexity and parameters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to predict future events in multiple related data streams (time series) is developed. This approach creates extra information from the original data that helps it understand relationships between different streams. The new method uses a simple neural network as its core predictor, but still outperforms previous methods while using fewer calculations and less data. |
Keywords
* Artificial intelligence * Deep learning * Neural network * Time series
