ChronoFlow is proposed, a unified hierarchical flow matching framework organized by statistical granularity that turns a complex joint generation problem into structurally aligned subproblems while preserving their dependencies.
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.
This work introduces a novel sampling-conditioned temporal manifold attention mechanism that maps real timestamps into a learnable temporal manifold feature space and injects temporal manifold biases into attention layers, enabling the model to capture both irregular time intervals and local sampling structures.
Lin-Feng Wang, Rui-Tong Zhang, Kai Zhao et al.· 0 citations
Rondo is introduced, an unsupervised approach for modeling recurring hierarchical structure in continuous temporal streams that outperforms existing unsupervised recurrence-discovery baselines and provides a stronger foundation for recurring-pattern discovery, scalable behavior understanding, and adaptive intelligent s...
Ying-Tian Shi, Ankith Chandra, T. Plötz· 0 citations
A Constraint-Guided Dynamic Graph Network (ConDyGNet), whose core idea is “global basis, dynamic weights”, which learns a low-rank global basis as a shared structural constraint and generates patch-wise basis mixing weights to construct dynamic propagation graphs.
Zhen-Zhou Li, Xiang Li, Zhibin Niu· Proceedings of the Thirty-Fi...· 0 citations
Results show that replacing or augmenting the original training set with SI-CVAE–generated data yields consistent accuracy gains across multiple forecasting baselines, and that SI-CVAE attains higher synthetic-data quality than state-of-the-art generators on standard metrics.
Jian-Ping Zhu, Lei Wang, Yang Chen et al.· 0 citations
This work proposes Liquid Gated Attention (LGA), a solver-free parallel temporal operator that introduces a continuous-time inductive bias and formulates hidden state evolution as a fast-weight associative memory, enabling parallel computation across the temporal dimension.
Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerg...
Shi-Bo Feng, Wan-Jin Feng, Yang Qiu et al.· 0 citations