LMS-AutoTSF: Learnable Multi-Scale Decomposition and Integrated Autocorrelation for Time Series Forecasting

2024-12-09

AI Summary

Addressing the challenges of dynamically decoupling long-term trends and seasonal components, as well as insufficient modeling of short- and long-range dependencies in multi-scale time series forecasting, this paper proposes LMS-AutoTSF. Methodologically, it introduces: (1) a novel learnable multi-scale frequency-domain decomposition framework, employing end-to-end optimized high-pass and low-pass filters for adaptive trend-seasonality separation; (2) the first integration of the self-correlation mechanism into a dual-encoder architecture, augmented with lagged differencing to enhance periodicity and abrupt-change detection; and (3) a fully connected spatio-temporal–channel interaction layer to improve modeling efficiency. Evaluated on multiple benchmark datasets, LMS-AutoTSF achieves statistically significant accuracy gains over state-of-the-art methods, reduces parameter count by over 30%, and accelerates inference by 2.1×—demonstrating both superior predictive performance and lightweight deployment capability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Learning & Optimization for NLP
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Time series forecasting is an important challenge with significant applications in areas such as weather prediction, stock market analysis, scientific simulations and industrial process analysis. In this work, we introduce LMS-AutoTSF, a novel time series forecasting architecture that incorporates autocorrelation while leveraging dual encoders operating at multiple scales. Unlike models that rely on predefined trend and seasonal components, LMS-AutoTSF employs two separate encoders per scale: one focusing on low-pass filtering to capture trends and the other utilizing high-pass filtering to model seasonal variations. These filters are learnable, allowing the model to dynamically adapt and isolate trend and seasonal components directly in the frequency domain. A key innovation in our approach is the integration of autocorrelation, achieved by computing lagged differences in time steps, which enables the model to capture dependencies across time more effectively. Each encoder processes the input through fully connected layers to handle temporal and channel interactions. By combining frequency-domain filtering, autocorrelation-based temporal modeling, and channel-wise transformations, LMS-AutoTSF not only accurately captures long-term dependencies and fine-grained patterns but also operates more efficiently compared to other state-of-the-art methods. Its lightweight design ensures faster processing while maintaining high precision in forecasting across diverse time horizons. The source code is publicly available at url{http://github.com/mribrahim/LMS-TSF}

Problem

• Time Series Prediction
• Long-term Trends
• Adaptive Forecasting

Innovation

• LMS-AutoTSF
• Multi-scale Decomposition
• Autocorrelation Integration