A0951
Title: Tensor-augmented transformers for multi-dimensional time series forecasting
Authors: Yuefeng Han - University of Notre Dame (United States) [presenting]
Abstract: Multi-dimensional time series data, such as matrix and tensor-valued 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, the tensor-augmented transformer (TEAFormer) is introduced, 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 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.
