Bridging Simplicity and Sophistication using GLinear: A Novel Architecture for Enhanced Time Series Prediction

2025-01-02

AI Summary

Addressing the challenges of modeling periodic patterns, limited historical data, and high model complexity in multivariate time series forecasting, this paper proposes GLinear—a minimalist yet period-aware linear architecture. Its core innovation lies in the first integration of learnable periodic decomposition with a multi-scale trend-period disentanglement mechanism into a lightweight linear model, augmented by parameter-efficient temporal projection to significantly enhance periodic modeling capability and data efficiency. Evaluated on four major benchmarks—ETTh1, Electricity, Traffic, and Weather—GLinear consistently outperforms state-of-the-art methods including NLinear, DLinear, RLinear, and Autoformer. It achieves an average 12.7% reduction in prediction error, reduces trainable parameters by over 90%, and demonstrates superior accuracy, generalization, and computational efficiency.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Time Series Forecasting (TSF) is an important application across many fields. There is a debate about whether Transformers, despite being good at understanding long sequences, struggle with preserving temporal relationships in time series data. Recent research suggests that simpler linear models might outperform or at least provide competitive performance compared to complex Transformer-based models for TSF tasks. In this paper, we propose a novel data-efficient architecture, GLinear, for multivariate TSF that exploits periodic patterns to provide better accuracy. It also provides better prediction accuracy by using a smaller amount of historical data compared to other state-of-the-art linear predictors. Four different datasets (ETTh1, Electricity, Traffic, and Weather) are used to evaluate the performance of the proposed predictor. A performance comparison with state-of-the-art linear architectures (such as NLinear, DLinear, and RLinear) and transformer-based time series predictor (Autoformer) shows that the GLinear, despite being parametrically efficient, significantly outperforms the existing architectures in most cases of multivariate TSF. We hope that the proposed GLinear opens new fronts of research and development of simpler and more sophisticated architectures for data and computationally efficient time-series analysis. The source code is publicly available on GitHub.

Problem

• Multivariate Time Series Prediction
• Periodic Patterns
• Computational Efficiency

Innovation

• GLinear
• Time Series Prediction
• Multi-variable Forecasting