Synthetic Time Series Generation via Complex Networks

2026-01-30

AI Summary

High-quality time series data are often scarce due to privacy concerns, high acquisition costs, and the difficulty of annotation. To address this challenge, this work proposes an interpretable synthetic data generation method based on quantile graphs: it maps time series into complex network structures and then reconstructs the data through an inverse mapping, effectively preserving the original statistical and dynamic properties. Unlike conventional black-box generative models, the proposed approach offers enhanced interpretability and structural fidelity. Extensive experiments on both simulated and real-world datasets demonstrate that the generated data achieve high fidelity and practical utility, matching the performance of state-of-the-art GAN-based methods while providing superior interpretability and better preservation of intrinsic temporal structures.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Time series data are essential for a wide range of applications, particularly in developing robust machine learning models. However, access to high-quality datasets is often limited due to privacy concerns, acquisition costs, and labeling challenges. Synthetic time series generation has emerged as a promising solution to address these constraints. In this work, we present a framework for generating synthetic time series by leveraging complex networks mappings. Specifically, we investigate whether time series transformed into Quantile Graphs (QG) -- and then reconstructed via inverse mapping -- can produce synthetic data that preserve the statistical and structural properties of the original. We evaluate the fidelity and utility of the generated data using both simulated and real-world datasets, and compare our approach against state-of-the-art Generative Adversarial Network (GAN) methods. Results indicate that our quantile graph-based methodology offers a competitive and interpretable alternative for synthetic time series generation.

Problem

• Synthetic Time Series
• Data Privacy
• Time Series Generation
• Statistical Properties
• Structural Properties

Innovation

• synthetic time series
• complex networks
• quantile graph
• inverse mapping
• interpretable generation