SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
This work addresses a bottleneck in time series forecasting for domains like finance or weather, offering a more efficient RNN-based method, though it is incremental as it builds on existing RNN strategies.
The paper tackles the challenge of long-term time series forecasting with RNNs by proposing SegRNN, which reduces recurrent iterations through segment-wise iterations and parallel multi-step forecasting, resulting in improved accuracy and over 78% reductions in runtime and memory usage compared to SOTA Transformer models.
RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards Transformer, MLP, and CNN approaches. The substantial number of recurrent iterations are the fundamental reasons behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF). RNNs that combine these strategies, namely SegRNN, significantly reduce the required recurrent iterations for LTSF, resulting in notable improvements in forecast accuracy and inference speed. Extensive experiments demonstrate that SegRNN not only outperforms SOTA Transformer-based models but also reduces runtime and memory usage by more than 78%. These achievements provide strong evidence that RNNs continue to excel in LTSF tasks and encourage further exploration of this domain with more RNN-based approaches. The source code is coming soon.