Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs

ArXi:2603.19970v1 Announce Type: cross Although recent generative models can produce time series with close marginal distributions, they often face a fundamental tension between preserving global temporal structure and modeling stochastic local variations, particularly for highly volatile signals with weak or irregular periodicity. Direct distribution matching in such settings can amplify noise or suppress meaningful temporal patterns.