ChronoFlow improves generation of irregular time series data
ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation
Artificial Intelligence
Summary
Irregular time series are sets of observations made at uneven times and with varying features, making them tricky to simulate realistically. The authors introduce ChronoFlow, a method that generates these series step-by-step, first deciding how many observations happen and which features appear together, then when they happen, and finally what their values are. This approach simplifies the complex challenge of creating realistic irregular data. The authors also designed new ways to measure how well these generated series match real ones and showed that ChronoFlow performs better than existing methods.
What this means in practice
- •For healthcare data engineers: Generate realistic irregular patient monitoring data for testing and validating analytics systems.
- •For financial modelers: Simulate irregularly sampled financial market indicators capturing timing and feature dependencies for risk assessment.
Authors
Changhun Kim, Sunguk Jang, Jeongjun Lee, Juhwan Choi, Sangchul Hahn, Grigorios Chrysos, Eunho Yang, Juho Lee
Abstract
Recent advances in generative modeling have substantially improved time series generation, yet most existing methods either assume a regular temporal grid or focus on feature dynamics under a given sampling structure. This makes them illsuited for generating irregular time series in their native form, where a model must capture not only feature values, but also how many observations occur, when they occur, and which features are observed together. To address this heterogeneous generation problem, we propose ChronoFlow, a unified hierarchical flow matching framework organized by statistical granularity. Following a coarse-to-fine hierarchy, ChronoFlow first generates observation counts and feature-wise frequencies, then jointly generates observation times and feature co-observation patterns, and finally generates values conditioned on the realized pattern. This turns a complex joint generation problem into structurally aligned subproblems while preserving their dependencies. To evaluate complete irregular time series generation, we introduce complementary metrics spanning sample realism, sampling structure, value fidelity, and temporal and cross-feature dependencies, and validate them through controlled corruptions. Across five benchmarks, ChronoFlow achieves strong improvements in generation fidelity over existing baselines, while factorization studies support the proposed hierarchy. Our code is available at https://anonymous.4open.science/r/ChronoFlow.