Graph Neural Alchemist: An innovative fully modular architecture for time series-to-graph classification

TL;DR

This paper presents a fully modular Graph Neural Network architecture that uses visibility graph representations to efficiently classify time series data, capturing complex dependencies and outperforming traditional methods.

Contribution

It introduces a novel GNN architecture based on visibility graphs with directed features, enhancing time series classification with improved efficiency and dependency modeling.

Findings

Robustness across diverse classification tasks

Enhanced capture of long-range dependencies

Outperforms traditional models in accuracy and efficiency

Abstract

This paper introduces a novel Graph Neural Network (GNN) architecture for time series classification, based on visibility graph representations. Traditional time series classification methods often struggle with high computational complexity and inadequate capture of spatio-temporal dynamics. By representing time series as visibility graphs, it is possible to encode both spatial and temporal dependencies inherent to time series data, while being computationally efficient. Our architecture is fully modular, enabling flexible experimentation with different models and representations. We employ directed visibility graphs encoded with in-degree and PageRank features to improve the representation of time series, ensuring efficient computation while enhancing the model's ability to capture long-range dependencies in the data. We show the robustness and generalization capability of the proposed architecture across a diverse set of classification tasks and against a traditional model. Our work represents a significant advancement in the application of GNNs for time series analysis, offering a powerful and flexible framework for future research and practical implementations.