Summary of Time and Frequency Synergy For Source-free Time-series Domain Adaptations, by Muhammad Tanzil Furqon et al.
Time and Frequency Synergy for Source-Free Time-Series Domain Adaptations
by Muhammad Tanzil Furqon, Mahardhika Pratama, Ary Mazharuddin Shiddiqi, Lin Liu, Habibullah Habibullah, Kutluyil Dogancay
First submitted to arxiv on: 23 Oct 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 proposed Time Frequency Domain Adaptation (TFDA) method addresses source-free time-series domain adaptation issues by leveraging both time and frequency features. A dual branch network structure is developed to combine these features, generating pseudo-labels through neighborhood aggregation and contrastive learning. Additionally, self-distillation, uncertainty reduction, and curriculum learning strategies are integrated to improve the approach’s robustness. Experimental results demonstrate TFDA’s advantage over prior arts in benchmark problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way of adapting time-series data is developed, called Time Frequency Domain Adaptation (TFDA). This method looks at both the timing and frequency parts of the data to make predictions. It creates fake labels by averaging together predictions from similar groups and uses these labels along with a special learning technique to improve its accuracy. The approach also reduces uncertainty caused by changes in the data and helps learn from noisy information. Tests show that TFDA performs better than previous methods in certain tasks. |
Keywords
» Artificial intelligence » Curriculum learning » Distillation » Domain adaptation » Time series
