IMPROVING MULTI-VARIATE TIME SERIES FORECASTING WITH DYNAMIC MULTI-HEAD ATTENTION ADJACENCY MATRIX

Time series data is prevalent in many fields, such as finance, weather forecasting, and economics. Predicting future values of a time series can offer valuable insights for decision-making, such as identifying trends, detecting anomalies, and improving resource allocation. Existing research, including neural network-based models and transformer-based models, has demonstrated high performance in learning temporal information. However, capturing spatial information within time series data remains a significant challenge. In this project, we explored whether the attention mechanism can be effectively integrated into non-transformer-based models to enhance their ability to learn spatial information. To achieve this goal, we propose a novel framework that uses a dynamically learned adjacency matrix based on related work called the Multi-variate Time-series Graph Neural Network(MTGNN). Instead of using a correlation-based learned adjacency matrix, the adjacency matrix and graph modules are replaced with a dynamically learned adjacency matrix with multi-attention. This framework shows that a dynamically learned attention adjacency matrix can perform as well as other frameworks when learning spatial information.

Department dc:contributor.department

Computer Science

Grantor dc:publisher

East Carolina University

Year dc:date.issued

2025

Author dc:creator

• Bruce, Ashley Denise

Advisor dc:contributor.advisor

• Ding, Qin

Committee members dc:contributor.committeemember

• Dr. Sinan Sousan
• Dr. Nic Herndon

• attention

Handle dc:identifier.uri

http://hdl.handle.net/10342/14041

OAI identifier oai:identifier

oai:thescholarship.ecu.edu:10342/14041