Learning Fast and Slow for Online Time Series Forecasting

Page view(s)
Checked on Jun 04, 2024
Learning Fast and Slow for Online Time Series Forecasting
Learning Fast and Slow for Online Time Series Forecasting
Journal Title:
International Conference on Learning Representations
Publication Date:
31 May 2023
Pham, Quang, et al. "Learning Fast and Slow for Online Time Series Forecasting." The Eleventh International Conference on Learning Representations. 2023.
Despite the recent success of deep learning for time series forecasting, these methods are not scalable for many real-world applications where data arrives sequentially. Training deep neural forecasters on the fly is notoriously challenging because of their limited ability to adapt to non-stationary environments and remember old knowledge. We argue that the fast adaptation capability of deep neural networks is critical and successful solutions require handling changes to both new and recurring patterns effectively. In this work, inspired by the Complementary Learning Systems (CLS) theory, we propose Fast and Slow learning Network (FSNet) as a novel framework to address the challenges of online forecasting. Particularly, FSNet improves the slowly-learned backbone by dynamically balancing fast adaptation to recent changes and retrieving similar old knowledge. FSNet achieves this mechanism via an interaction between two novel complementary components: (i) a per-layer adapter to support fast learning from individual layers, and (ii) an associative memory to support remembering, updating, and recalling repeating events. Extensive experiments on real and synthetic datasets validate FSNet's efficacy and robustness to both new and recurring patterns. Our code is publicly available at: \url{https://github.com/salesforce/fsnet/}.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Files uploaded:

File Size Format Action
4220-learning-fast-and-slow-for-onl.pdf 738.58 KB PDF Open
11198.png 994.95 KB PNG Open