CometNet: Contextual Motif-guided Long-term Time Series Forecasting

TL;DR

CometNet introduces a novel framework that leverages recurrent contextual motifs from historical data to improve long-term time series forecasting, overcoming the limitations of traditional models' look-back windows.

Contribution

The paper proposes a new motif-guided approach that identifies and integrates dominant temporal motifs for enhanced long-term forecasting accuracy.

Findings

Outperforms state-of-the-art methods on eight real-world datasets

Significantly improves forecasting accuracy for extended horizons

Effectively captures long-term dependencies beyond limited look-back windows

Abstract

Long-term Time Series Forecasting is crucial across numerous critical domains, yet its accuracy remains fundamentally constrained by the receptive field bottleneck in existing models. Mainstream Transformer- and Multi-layer Perceptron (MLP)-based methods mainly rely on finite look-back windows, limiting their ability to model long-term dependencies and hurting forecasting performance. Naively extending the look-back window proves ineffective, as it not only introduces prohibitive computational complexity, but also drowns vital long-term dependencies in historical noise. To address these challenges, we propose CometNet, a novel Contextual Motif-guided Long-term Time Series Forecasting framework. CometNet first introduces a Contextual Motif Extraction module that identifies recurrent, dominant contextual motifs from complex historical sequences, providing extensive temporal dependencies far exceeding limited look-back windows; Subsequently, a Motif-guided Forecasting module is proposed, which integrates the extracted dominant motifs into forecasting. By dynamically mapping the look-back window to its relevant motifs, CometNet effectively harnesses their contextual information to strengthen long-term forecasting capability. Extensive experimental results on eight real-world datasets have demonstrated that CometNet significantly outperforms current state-of-the-art (SOTA) methods, particularly on extended forecast horizons.