Summary of Shapeformer: Shapelet Transformer For Multivariate Time Series Classification, by Xuan-may Le et al.
ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification
by Xuan-May Le, Ling Luo, Uwe Aickelin, Minh-Tuan Tran
First submitted to arxiv on: 23 May 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 proposes a novel approach to multivariate time series classification (MTSC) using transformers. The existing methods focus on generic features, but ignore class-specific features that are crucial for learning the representative characteristics of each class. To address this, the authors introduce the Shapelet Transformer (ShapeFormer), which combines class-specific and generic transformer modules. The class-specific module extracts discriminative subsequences (shapelets) from the training set, while the generic module uses convolution filters to extract generic features. The combination of these two modules enables the model to exploit both types of features, enhancing classification performance. The authors evaluate ShapeFormer on 30 UEA MTSC datasets and achieve state-of-the-art accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to classify complex time series data using a type of artificial intelligence called transformers. Currently, most methods focus on general patterns in the data, but ignore important details that make each class unique. The authors create a new model called ShapeFormer that looks at both general and specific features to improve classification accuracy. They test their model on 30 different datasets and show that it performs better than existing methods. |
Keywords
» Artificial intelligence » Classification » Time series » Transformer
