Summary of Shapelet-based Model-agnostic Counterfactual Local Explanations For Time Series Classification, by Qi Huang et al.
Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification
by Qi Huang, Wei Chen, Thomas Bäck, Niki van Stein
First submitted to arxiv on: 2 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper proposes a new method for explaining time series classification models. The approach, called Time-CF, is model-agnostic, meaning it can be used with any existing time series classifier. It uses two techniques: shapelets and TimeGAN, to generate counterfactual instances that provide insights into the decision-making process of the model. The authors evaluate their method on several real-world datasets from the UCR Time Series Archive and show that it outperforms state-of-the-art methods in terms of four explainability metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making machines understandable. It’s like trying to figure out why a machine made a certain decision, even if you didn’t program it yourself. The researchers developed a new way to do this for time series data, which is used for forecasting and analyzing patterns in things like stock prices or weather. They tested their method on several datasets and found that it works better than other methods at explaining what the machine did. |
Keywords
* Artificial intelligence * Classification * Time series
