Tag
ReGeN is a reference-guided generative pipeline for multivariate time series data that decomposes observed sequences into periodic backbone, stochastic residuals, and cross-variable dependencies to synthesize controllable synthetic data. It demonstrates that generated data can substitute for real data in forecasting tasks, outperforming prior synthetic data generators.
This paper introduces a diagnostic framework for multivariate time series anomaly detection benchmarks and finds that labeled anomalies are mostly detectable from individual channels, challenging the need for cross-channel modeling. The authors call for more structurally diverse evaluation sets.
This paper introduces TSCOMP, a large-scale benchmark that systematically decomposes deep multivariate time-series forecasting methods into fine-grained components to enable automated model selection, outperforming complex holistic architectures.