Summary of Dataset Condensation For Time Series Classification Via Dual Domain Matching, by Zhanyu Liu et al.
Dataset Condensation for Time Series Classification via Dual Domain Matching
by Zhanyu Liu, Ke Hao, Guanjie Zheng, Yanwei Yu
First submitted to arxiv on: 12 Mar 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 The paper proposes a novel framework for condensing large time series datasets for efficient training of deep neural networks. The technique, called Dataset Condensation for Time Series Classification via Dual Domain Matching (CondTSC), focuses on generating synthetic datasets that match the original data in both time and frequency domains. This is achieved through multi-view data augmentation, dual domain training, and dual surrogate objectives. The authors demonstrate the effectiveness of their framework by comparing it to other baselines, showing improved performance and desirable characteristics such as conforming to the distribution of the original data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make computers learn from big collections of time series data, like stock prices or weather patterns. This method is called Dataset Condensation for Time Series Classification via Dual Domain Matching (CondTSC). It makes a smaller version of the real dataset that can be used to train a deep neural network quickly and efficiently. The authors did this by combining different techniques, like making fake data, training in both time and frequency domains, and using special objectives. They showed that their method works better than others and creates synthetic datasets that match the original data. |
Keywords
* Artificial intelligence * Classification * Data augmentation * Neural network * Time series
