Unlocking the Power of LSTM for Long Term Time Series Forecasting
This work addresses long-term forecasting challenges for time series analysis, representing an incremental improvement over existing methods.
The paper tackled the short memory issue of sLSTM in time series forecasting by proposing P-sLSTM, which incorporates patching and channel independence, achieving state-of-the-art results.
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.