Complex Networks Turn Time Series Into Synthetic Data With a Quantile Graph Twist

Synthetic data has become one of the most quietly transformative ideas in modern machine learning, and a new study from the University of Porto and INESC TEC suggests that one of its most powerful engines may not be a neural network at all, but a graph. In research published in the International Journal of Data Science and Analytics, Jaime Vale, Vanessa Freitas Silva, Maria Eduarda Silva and Fernando Silva systematically evaluated a deceptively simple framework called the Inverse Quantile Graph, or InvQG, which converts a real-world time series into a complex network and then runs the mapping backwards to generate brand-new, statistically faithful synthetic sequences. The work arrives at a moment when demand for synthetic time series is surging across energy grids, healthcare monitoring, finance and smart-meter analytics, precisely because real temporal data is so often locked away behind privacy walls, acquisition costs and labeling bottlenecks.

The core insight behind the approach traces back to a duality first described more than a decade ago: any time series can be transformed into a network, and that network can, in principle, be transformed back. The Quantile Graph representation, developed and refined by the Porto team in earlier work, partitions the range of observed values into quantile-based nodes and connects nodes whenever consecutive observations of the series fall into the corresponding bins. The result is a compact graph that encodes both the marginal distribution of values and the short-term transition structure of the dynamics. Where the original mapping was designed for analysis, extracting network-based features that characterize everything from EEG signals to electricity consumption, the inverse mapping asks a different question: if you know the graph, can you walk it to produce a plausible new series?

Answering that question rigorously is the central contribution of the new study. Although the inverse Quantile Graph mapping had been proposed before, its potential as a general-purpose data generator had never been systematically tested. The researchers assembled a comprehensive empirical evaluation spanning simulated and real-world datasets, comparing synthetic output against the originals across three complementary dimensions: classical statistical features, network-based topological characteristics, and practical utility in downstream clustering and classification tasks. This tri-fold evaluation matters because a synthetic generator can look convincing on one axis while failing badly on another; a series may preserve its histogram perfectly yet lose the long-memory behavior that makes it useful for forecasting experiments.

The simulated benchmark covered a deliberately broad zoo of generative processes, including white noise, first-order autoregressive models with coefficients ranging from strongly negative to strongly positive, ARIMA and ARFIMA processes, GARCH volatility models, self-exciting threshold autoregressive SETAR dynamics and integer-valued INAR count series. This diversity was not incidental. Each model stresses a different property of the generator: ARFIMA probes long-range dependence, GARCH probes heteroskedastic volatility clustering, SETAR probes nonlinear regime switching, and INAR probes discrete-valued behavior that many continuous generators handle poorly. By testing across all of them, the team could map precisely where InvQG shines and where its edges fray.

The headline finding is encouraging for practitioners. InvQG effectively preserves marginal distributions and short-term temporal dependencies across a wide range of models, meaning the synthetic series match the originals in their value histograms, their autocorrelation structure at short lags and their overall visual texture. On the real-world side, the team used one-minute resolution domestic electricity consumption data from the UK Data Service, covering dozens of households, a domain where privacy concerns are acute and synthetic alternatives are genuinely valuable. Here, too, the framework held its own, and comparisons with TimeGAN, a prominent deep-learning generator for time series, showed InvQG producing synthetic data whose embedding structure remained competitive, all without a single gradient step or GPU hour.

That computational simplicity is part of the appeal. Generative adversarial networks and variational autoencoders dominate the synthetic time series literature, but they bring well-documented burdens: training instability, mode collapse, hyperparameter sensitivity and opaque internal dynamics. InvQG, by contrast, is essentially deterministic in its construction and interpretable by design. The Quantile Graph is a human-readable object whose nodes and edges correspond directly to value ranges and observed transitions. When the generator produces something odd, an analyst can inspect the graph and understand why. For regulated industries such as energy and healthcare, where explainability is not optional, this transparency could prove as important as raw fidelity.

The study is equally candid about limitations, and that honesty strengthens its scientific value. The framework exhibits predictable weaknesses in capturing long-range or higher-order dynamics. Processes with slowly decaying autocorrelation, such as ARFIMA series with fractional integration, or nonlinear structures that depend on interactions beyond consecutive value transitions, are not fully reproduced by the quantile-based walk. This is a structural consequence of the representation itself: by binning values into quantile nodes and recording transitions between them, the graph naturally encodes first-order, short-memory structure, while higher-order temporal patterns are compressed away. The authors frame these limitations as predictable rather than fatal, giving users a clear decision rule for when the method is appropriate.

The evaluation methodology itself offers a template for the field. Rather than relying on eyeballing plots, the researchers combined feature-based statistical comparison, using established time series feature extraction tools, with Wilcoxon signed-rank tests to assess whether differences between synthetic and original features were statistically significant across many model-feature combinations, and with network-derived features that quantify the topological fingerprints of the generated graphs. Downstream tasks provided the final arbiter: if synthetic data can support clustering and classification as well as real data, it has genuine utility for model development, benchmarking and education. This multi-pronged validation stands in contrast to much of the GAN literature, where fidelity claims often rest on narrower evidence.

The practical implications extend well beyond the benchmark suite. For smart-meter and energy analytics, where individual consumption traces are sensitive personal data, a generator that preserves the statistical character of usage patterns without exposing any single household could unlock model sharing, algorithm benchmarking and anomaly-detection research on an unprecedented scale. For data augmentation in classification pipelines, where labeled time series are scarce and expensive, InvQG offers a lightweight way to expand training sets. And for the complex networks community, the results validate a decade-old intuition: that the duality between time series and networks is not merely an analytical curiosity but a two-way street with genuine generative power.

The team has released both code and data to make the results reproducible, with the InvQG implementation available on GitHub and the underlying datasets accessible through public repositories. Funded by the Portuguese Foundation for Science and Technology, the work signals a broader trend in which network science methods are migrating from descriptive analysis toward active roles in the generative data pipeline. As synthetic data becomes infrastructure for machine learning, the field will need generators that are fast, interpretable and honest about their failure modes. The Inverse Quantile Graph may not dethrone deep generative models for long-memory or highly nonlinear series, but as this study demonstrates, for the vast class of problems where marginals and short-term dynamics matter most, a well-built graph can be a remarkably capable data factory.

Subject of Research: Synthetic time series generation using inverse Quantile Graph complex network mappings

Article Title: Synthetic time series generation via complex networks

Article References: Vale, J., Silva, V. F., Silva, M. E., & Silva, F. (2026). Synthetic time series generation via complex networks. International Journal of Data Science and Analytics, 22(1), Article 299. https://doi.org/10.1007/s41060-026-01271-x

Image Credits: AI Generated

DOI: 10.1007/s41060-026-01271-x

Keywords: synthetic data, time series, complex networks, Quantile Graph, generative models, data privacy, TimeGAN, data augmentation, network science, machine learning, energy analytics, statistical fidelity