Time series forecasting with alternative backbone models and attention mechanisms

This project is an extension of the work done by Yeh et al. (2023). We explore the effectiveness of using alternative backbone architectures for creating a multi-domain foundation model for time series forecasting (WaveNet and TCNN) and whether architectures with attention mechanisms perform better than their non-attention counterparts.

© 2024 Sarah Q. & Sonal B.
University of Waterloo

Paper: Chin-Chia Michael Yeh, Xin Dai, Huiyuan Chen, Yan Zheng, Yujie Fan, Audrey Der, Vivian Lai, Zhongfang Zhuang, Junpeng Wang, Liang Wang, and Wei Zhang, "Toward a Foundation Model for Time Series Data," ACM International Conference on Information and Knowledge Management (CIKM), 2023