Saved in:
Bibliographic Details
Main Authors: Chen, Yang, Kempton, Dustin J., Angryk, Rafal A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.06576
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910361945374720
author Chen, Yang
Kempton, Dustin J.
Angryk, Rafal A.
author_facet Chen, Yang
Kempton, Dustin J.
Angryk, Rafal A.
contents The success of deep learning-based generative models in producing realistic images, videos, and audios has led to a crucial consideration: how to effectively assess the quality of synthetic samples. While the Fréchet Inception Distance (FID) serves as the standard metric for evaluating generative models in image synthesis, a comparable metric for time series data is notably absent. This gap in assessment capabilities stems from the absence of a widely accepted feature vector extractor pre-trained on benchmark time series datasets. In addressing these challenges related to assessing the quality of time series, particularly in the context of Fréchet Distance, this work proposes a novel solution leveraging the Fourier transform and Auto-encoder, termed the Fréchet Fourier-transform Auto-encoder Distance (FFAD). Through our experimental results, we showcase the potential of FFAD for effectively distinguishing samples from different classes. This novel metric emerges as a fundamental tool for the evaluation of generative time series data, contributing to the ongoing efforts of enhancing assessment methodologies in the realm of deep learning-based generative models.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06576
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FFAD: A Novel Metric for Assessing Generated Time Series Data Utilizing Fourier Transform and Auto-encoder
Chen, Yang
Kempton, Dustin J.
Angryk, Rafal A.
Machine Learning
The success of deep learning-based generative models in producing realistic images, videos, and audios has led to a crucial consideration: how to effectively assess the quality of synthetic samples. While the Fréchet Inception Distance (FID) serves as the standard metric for evaluating generative models in image synthesis, a comparable metric for time series data is notably absent. This gap in assessment capabilities stems from the absence of a widely accepted feature vector extractor pre-trained on benchmark time series datasets. In addressing these challenges related to assessing the quality of time series, particularly in the context of Fréchet Distance, this work proposes a novel solution leveraging the Fourier transform and Auto-encoder, termed the Fréchet Fourier-transform Auto-encoder Distance (FFAD). Through our experimental results, we showcase the potential of FFAD for effectively distinguishing samples from different classes. This novel metric emerges as a fundamental tool for the evaluation of generative time series data, contributing to the ongoing efforts of enhancing assessment methodologies in the realm of deep learning-based generative models.
title FFAD: A Novel Metric for Assessing Generated Time Series Data Utilizing Fourier Transform and Auto-encoder
topic Machine Learning
url https://arxiv.org/abs/2403.06576