Cascaded Teaching Transformers with Data Reweighting for Long Sequence Time-series Forecasting

Haoyi Zhou, Chonghan Gao, Pengtao Xie, Jianxin Li

Keywords: Teaching, Reweight, Time-series, Forecast

TL;DR: Cascaded Teaching Trasnformers

Abstract: The Transformer-based models have shown superior performance in the long sequence time-series forecasting problem. The sparsity assumption on self-attention dot-product reveals that not all inputs are equally significant for Transformers. Instead of implicitly utilizing weighted time-series, we build a new learning framework by cascaded teaching Transformers to reweight samples. We formulate the framework as a multi-level optimization and design three different dataset-weight generators. We perform extensive experiments on five datasets, which shows that our proposed method could significantly outperform the SOTA Transformers.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning