Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting

TL;DR

This paper introduces DRAGON, a novel encoder that uses Multivariate de Bruijn Graphs to discretize and encode time series data, enhancing neural models' ability to handle temporal heterogeneity and high dimensionality.

Contribution

The paper proposes a new symbolic graph framework, MdBGs, integrated into neural models to improve time series forecasting performance.

Findings

Enhanced forecasting accuracy with MdBG integration

Effective handling of high-dimensional, heterogeneous data

Open-source code available for reproducibility

Abstract

Time series forecasting remains a challenging task for foundation models due to temporal heterogeneity, high dimensionality, and the lack of inherent symbolic structure. In this work, we propose DRAGON (Discrete Representation and Augmented Graph encoding Over de BruijN Graphs), a novel encoder that introduces Multivariate de Bruijn Graphs (MdBGs) to bridge the gap between symbolic representations and neural modeling. DRAGON discretizes continuous input sequences and maps them onto a fixed graph structure, enabling dynamic context recovery via graph-based attention. Integrated as an auxiliary module within a dual-branch architecture, DRAGON augments conventional CNN-based encoders with symbolic, structure-aware representations. All code developed for this study is available at: https://github.com/KurbanIntelligenceLab/MultdBG-Time-Series-Library