Search papers, labs, and topics across Lattice.
The TSDS-Toolbox provides a unified framework for measuring time-series dataset similarity, addressing the fragmentation in existing benchmarking implementations. This toolbox facilitates systematic comparisons and allows users to extend functionality by adding custom datasets and similarity methods. Comprehensive experiments validate its effectiveness, making it a vital resource for researchers in time-series analysis.
A unified toolbox for time-series dataset similarity could revolutionize how researchers select and evaluate datasets for AI model fine-tuning.
The rapid advancement of artificial intelligence (AI) has significantly accelerated research in time-series analysis, particularly in forecasting, classification, and generation tasks. Recent models, especially foundation models, benefit from time-series dataset similarity due to its significant role in source dataset selection for fine-tuning. However, many existing implementations for benchmarking time-series dataset similarity methods are fragmented and difficult to extend. To address this, we present a unified framework, the Time-Series Dataset Similarity Toolbox (TSDS-Toolbox). Our work enables (1) systematic and reproducible comparisons of time-series dataset similarity methods; (2) flexible extensibility for users to add customized datasets, similarity methods, and downstream time-series tasks; and (3) consistent evaluation of both dataset-level and series-level similarity methods through integrated time-series dataset reducers. The effectiveness of TSDS-Toolbox is validated through comprehensive experiments under diverse experimental settings. Our toolbox is publicly available.
