xLSTMTime : Long-term Time Series Forecasting With xLSTM

TL;DR

This paper introduces xLSTMTime, a refined recurrent neural network architecture with exponential gating and enhanced memory, demonstrating superior long-term time series forecasting performance compared to transformer-based models across multiple datasets.

Contribution

The paper proposes xLSTMTime, an improved LSTM-based architecture with exponential gating and higher capacity memory, outperforming transformer models in long-term time series forecasting.

Findings

xLSTMTime outperforms state-of-the-art models on multiple datasets.

Refined recurrent architectures can rival transformer-based models in LTSF.

xLSTMTime demonstrates superior forecasting accuracy in long-term predictions.

Abstract

In recent years, transformer-based models have gained prominence in multivariate long-term time series forecasting (LTSF), demonstrating significant advancements despite facing challenges such as high computational demands, difficulty in capturing temporal dynamics, and managing long-term dependencies. The emergence of LTSF-Linear, with its straightforward linear architecture, has notably outperformed transformer-based counterparts, prompting a reevaluation of the transformer's utility in time series forecasting. In response, this paper presents an adaptation of a recent architecture termed extended LSTM (xLSTM) for LTSF. xLSTM incorporates exponential gating and a revised memory structure with higher capacity that has good potential for LTSF. Our adopted architecture for LTSF termed as xLSTMTime surpasses current approaches. We compare xLSTMTime's performance against various state-of-the-art models across multiple real-world da-tasets, demonstrating superior forecasting capabilities. Our findings suggest that refined recurrent architectures can offer competitive alternatives to transformer-based models in LTSF tasks, po-tentially redefining the landscape of time series forecasting.