TSGBench: Time Series Generation Benchmark

TL;DR

TSGBench is a comprehensive benchmark for evaluating time series generation methods, addressing current limitations by providing standardized datasets, diverse evaluation metrics, and a generalization test to facilitate fair and holistic comparisons.

Contribution

It introduces TSGBench, the first unified benchmark for TSG, with curated datasets, diverse evaluation measures, and a domain adaptation-based generalization test.

Findings

TSGBench effectively evaluates TSG methods across multiple datasets.

It reveals varying performance of methods depending on datasets and measures.

The benchmark provides nuanced insights into the strengths and weaknesses of different TSG approaches.

Abstract

Synthetic Time Series Generation (TSG) is crucial in a range of applications, including data augmentation, anomaly detection, and privacy preservation. Although significant strides have been made in this field, existing methods exhibit three key limitations: (1) They often benchmark against similar model types, constraining a holistic view of performance capabilities. (2) The use of specialized synthetic and private datasets introduces biases and hampers generalizability. (3) Ambiguous evaluation measures, often tied to custom networks or downstream tasks, hinder consistent and fair comparison. To overcome these limitations, we introduce \textsf{TSGBench}, the inaugural Time Series Generation Benchmark, designed for a unified and comprehensive assessment of TSG methods. It comprises three modules: (1) a curated collection of publicly available, real-world datasets tailored for TSG, together with a standardized preprocessing pipeline; (2) a comprehensive evaluation measures suite including vanilla measures, new distance-based assessments, and visualization tools; (3) a pioneering generalization test rooted in Domain Adaptation (DA), compatible with all methods. We have conducted comprehensive experiments using \textsf{TSGBench} across a spectrum of ten real-world datasets from diverse domains, utilizing ten advanced TSG methods and twelve evaluation measures. The results highlight the reliability and efficacy of \textsf{TSGBench} in evaluating TSG methods. Crucially, \textsf{TSGBench} delivers a statistical analysis of the performance rankings of these methods, illuminating their varying performance across different datasets and measures and offering nuanced insights into the effectiveness of each method.