TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kong, Linghang, Chen, Elynn, Chen, Yuzhou, Han, Yuefeng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913565527506944
author Kong, Linghang
Chen, Elynn
Chen, Yuzhou
Han, Yuefeng
author_facet Kong, Linghang
Chen, Elynn
Chen, Yuzhou
Han, Yuefeng
contents Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do not effectively preserve these multi-dimensional structures, as their internal operations in effect flatten multi-dimensional observations into vectors, thereby losing critical multi-dimensional relationships and patterns. To address this, we introduce the Tensor-Augmented Transformer (TEAFormer), a novel method that incorporates tensor expansion and compression within the Transformer framework to maintain and leverage the inherent multi-dimensional structures, thus reducing computational costs and improving prediction accuracy. The core feature of the TEAFormer, the Tensor-Augmentation (TEA) module, utilizes tensor expansion to enhance multi-view feature learning and tensor compression for efficient information aggregation and reduced computational load. The TEA module is not just a specific model architecture but a versatile component that is highly compatible with the attention mechanism and the encoder-decoder structure of Transformers, making it adaptable to existing Transformer architectures. Our comprehensive experiments, which integrate the TEA module into three popular time series Transformer models across three real-world benchmarks, show significant performance enhancements, highlighting the potential of TEAFormers for cutting-edge time series forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20439
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting
Kong, Linghang
Chen, Elynn
Chen, Yuzhou
Han, Yuefeng
Machine Learning
Artificial Intelligence
Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do not effectively preserve these multi-dimensional structures, as their internal operations in effect flatten multi-dimensional observations into vectors, thereby losing critical multi-dimensional relationships and patterns. To address this, we introduce the Tensor-Augmented Transformer (TEAFormer), a novel method that incorporates tensor expansion and compression within the Transformer framework to maintain and leverage the inherent multi-dimensional structures, thus reducing computational costs and improving prediction accuracy. The core feature of the TEAFormer, the Tensor-Augmentation (TEA) module, utilizes tensor expansion to enhance multi-view feature learning and tensor compression for efficient information aggregation and reduced computational load. The TEA module is not just a specific model architecture but a versatile component that is highly compatible with the attention mechanism and the encoder-decoder structure of Transformers, making it adaptable to existing Transformer architectures. Our comprehensive experiments, which integrate the TEA module into three popular time series Transformer models across three real-world benchmarks, show significant performance enhancements, highlighting the potential of TEAFormers for cutting-edge time series forecasting.
title TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.20439