Grasynda: Graph-based Synthetic Time Series Generation
This addresses the need for effective data augmentation in time series forecasting, especially for deep learning models, by providing a novel graph-based approach that preserves data properties better than existing methods.
The paper tackles the problem of limited training data in time series forecasting by introducing Grasynda, a graph-based method for synthetic time series generation that converts time series into a network structure and encodes temporal dynamics in a transition probability matrix. The results show that Grasynda consistently outperforms other data augmentation methods on six benchmark datasets with three neural network variations.
Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. However, extensive datasets are not always available in real-world scenarios. Although many data augmentation methods exist, their limitations include the use of transformations that do not adequately preserve data properties. This paper introduces Grasynda, a novel graph-based approach for synthetic time series generation that: (1) converts univariate time series into a network structure using a graph representation, where each state is a node and each transition is represented as a directed edge; and (2) encodes their temporal dynamics in a transition probability matrix. We performed an extensive evaluation of Grasynda as a data augmentation method for time series forecasting. We use three neural network variations on six benchmark datasets. The results indicate that Grasynda consistently outperforms other time series data augmentation methods, including ones used in state-of-the-art time series foundation models. The method and all experiments are publicly available.