ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation

TL;DR

ConTSG-Bench introduces a comprehensive benchmark dataset and evaluation framework for conditional time series generation, facilitating systematic assessment of models' fidelity and adherence across diverse conditions and revealing key challenges and future directions.

Contribution

This paper presents the first large-scale, standardized benchmark for evaluating conditional time series generation models across multiple modalities and conditions.

Findings

Current models show limitations in structural controllability.

Benchmark reveals trade-offs between fidelity and condition adherence.

Analysis highlights promising research directions for complex conditions.

Abstract

Conditional time series generation plays a critical role in addressing data scarcity and enabling causal analysis in real-world applications. Despite its increasing importance, the field lacks a standardized and systematic benchmarking framework for evaluating generative models across diverse conditions. To address this gap, we introduce the Conditional Time Series Generation Benchmark (ConTSG-Bench). ConTSG-Bench comprises a large-scale, well-aligned dataset spanning diverse conditioning modalities and levels of semantic abstraction, first enabling systematic evaluation of representative generation methods across these dimensions with a comprehensive suite of metrics for generation fidelity and condition adherence. Both the quantitative benchmarking and in-depth analyses of conditional generation behaviors have revealed the traits and limitations of the current approaches, highlighting critical challenges and promising research directions, particularly with respect to precise structural controllability and downstream task utility under complex conditions.