PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting

TL;DR

PSformer is a novel transformer model for time series forecasting that uses parameter sharing and segment attention to improve efficiency, scalability, and accuracy across various datasets.

Contribution

The paper introduces PSformer, combining parameter sharing and spatial-temporal segment attention to enhance time series forecasting performance and model efficiency.

Findings

Outperforms existing transformer-based models in accuracy.

Reduces training parameters significantly.

Demonstrates scalability on benchmark datasets.

Abstract

Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies. This paper presents a novel transformer architecture for time series forecasting, incorporating two key innovations: parameter sharing (PS) and Spatial-Temporal Segment Attention (SegAtt). We also define the time series segment as the concatenation of sequence patches from the same positions across different variables. The proposed model, PSformer, reduces the number of training parameters through the parameter sharing mechanism, thereby improving model efficiency and scalability. The introduction of SegAtt could enhance the capability of capturing local spatio-temporal dependencies by computing attention over the segments, and improve global representation by integrating information across segments. The combination of parameter sharing and SegAtt significantly improves the forecasting performance. Extensive experiments on benchmark datasets demonstrate that PSformer outperforms popular baselines and other transformer-based approaches in terms of accuracy and scalability, establishing itself as an accurate and scalable tool for time series forecasting.