TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers

arXiv:2307.12667v2 Announce Type: replace
Abstract: The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion, a diffusion, and transformers-based …

abstract adversarial applications arxiv convolutional neural network cs.lg data diffusion diffusion models fidelity gan generative generative adversarial networks however network networks neural network quality series time series transformers type