Summary of Addressing Concept Shift in Online Time Series Forecasting: Detect-then-adapt, by Yifan Zhang et al.
Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt
by YiFan Zhang, Weiqi Chen, Zhaoyang Zhu, Dalin Qin, Liang Sun, Xue Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
First submitted to arxiv on: 22 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 This paper proposes a novel approach called Concept Drift Detection and Adaptation (D3A) to tackle the challenge of concept drifting in time series forecasting models. D3A first detects drifting concepts and then aggressively adapts the current model to the drifted concepts for rapid adaptation. To harness the utility of historical data, the authors propose a data augmentation strategy introducing Gaussian noise into existing training instances. This helps mitigate the data distribution gap that contributes to train-test performance inconsistency. Theoretical analysis verifies the significance of this approach. Empirical studies across six datasets demonstrate the effectiveness of D3A in improving model adaptation capability, reducing the average Mean Squared Error (MSE) by 43.9% compared to a simple Temporal Convolutional Network (TCN) baseline and 33.3% compared to state-of-the-art models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making time series forecasting models better. Sometimes these models get stuck because the data they’re using is no longer relevant. The authors came up with a new way to detect when this happens and then update the model so it can make better predictions again. They also added some noise to old training data to help the model learn from that data better. This helped their method work even better than some other approaches. |
Keywords
* Artificial intelligence * Convolutional network * Data augmentation * Mse * Time series
