Sig-Graph GAN integrates signatures, LSTM, and GNNs on visibility graphs to generate synthetic financial time series that better match log-return distributions than baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Generative Adversarial Graph Neural Network for Synthetic Time Series Data
Sig-Graph GAN integrates signatures, LSTM, and GNNs on visibility graphs to generate synthetic financial time series that better match log-return distributions than baselines.