GAT-GAN : A Graph-Attention-based Time-Series Generative Adversarial Network
Authors:
Preprint
Abstract
Generative Adversarial Networks (GANs) have proven to be a powerful tool for generating realistic synthetic data. However, traditional GANs often struggle to capture complex relationships between features which results in generation of unrealistic multivariate time-series data. In this paper, we propose a Graph-Attention-based Generative Adversarial Network (GAT-GAN) that explicitly includes two graph-attention layers, one that learns temporal dependencies while the other captures spatial relationships. Unlike RNN-based GANs that struggle with modeling long sequences of data points, GAT-GAN generates long time-series data of high fidelity using an adversarially trained autoencoder architecture. Our empirical evaluations, using a variety of real-time-series datasets, show that our framework consistently outperforms state-of-the-art benchmarks based on \emph{Frechet Transformer distance} and \emph{Predictive score}, that characterizes (\emph{Fidelity, Diversity}) and \emph{predictive performance} respectively. Moreover, we introduce a Frechet Inception distance-like (FID) metric for time-series data called Frechet Transformer distance (FTD) score (lower is better), to evaluate the quality and variety of generated data. We also found that low FTD scores correspond to the best-performing downstream predictive experiments. Hence, FTD scores can be used as a standardized metric to evaluate synthetic time-series data.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Theoretical Limitations of Self-Attention in Neural Sequence ModelsTransactions of the Association for Computational Linguistics, 2020
- Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN)Energy and Buildings, 2020
- Quant GANs: deep generation of financial time seriesQuantitative Finance, 2020
- A Style-Based Generator Architecture for Generative Adversarial NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Spatio-temporal violent event prediction using Gaussian process regressionJournal of Computational Social Science, 2018
- Traveling Officer Problem: Managing Car Parking Violations Efficiently Using Sensor DataIEEE Internet of Things Journal, 2017
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001