Unlocking the Power of LSTM for Long Term Time Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912243197673472 |
|---|---|
| author | Kong, Yaxuan Wang, Zepu Nie, Yuqi Zhou, Tian Zohren, Stefan Liang, Yuxuan Sun, Peng Wen, Qingsong |
| author_facet | Kong, Yaxuan Wang, Zepu Nie, Yuqi Zhou, Tian Zohren, Stefan Liang, Yuxuan Sun, Peng Wen, Qingsong |
| contents | Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10006 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unlocking the Power of LSTM for Long Term Time Series Forecasting Kong, Yaxuan Wang, Zepu Nie, Yuqi Zhou, Tian Zohren, Stefan Liang, Yuxuan Sun, Peng Wen, Qingsong Machine Learning Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model. |
| title | Unlocking the Power of LSTM for Long Term Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.10006 |