Summary of Gla-da: Global-local Alignment Domain Adaptation For Multivariate Time Series, by Gang Tu et al.
GLA-DA: Global-Local Alignment Domain Adaptation for Multivariate Time Series
by Gang Tu, Dan Li, Bingxin Lin, Zibin Zheng, See-Kiong Ng
First submitted to arxiv on: 9 Oct 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 addresses the challenge of adapting time series data to a new domain without labor-intensive label annotations. Unsupervised and Semi-supervised Domain Adaptation (UDA and SSDA) have been effective in utilizing pre-labeled source data for training on unlabeled or partially labeled target data, but existing methods compromise performance when directly adapting labeled source samples with unlabelled target samples. The authors investigate the limitations of these methods and explore alternative approaches to ensure domain adaptation without sacrificing the performance of downstream classification tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making it easier to use time series data in new situations without having to label all the data by hand. Right now, we can do this with images and words, but not with time series data. Some methods have been developed to help with this problem, like using pre-labeled data to train on unlabeled or partially labeled new data. But these methods can actually make things worse if they’re not careful. The authors are trying to figure out why this is happening and how we can do better. |
Keywords
» Artificial intelligence » Classification » Domain adaptation » Semi supervised » Time series » Unsupervised
