Paper Detail
Shuang Liang, Chaochuan Hou, Xu Yao, Shiping Wang, Hailiang Huang, Songqiao Han, Minqi Jiang
While previous research in multivariate time series forecasting has focused on developing complex holistic models, this work advocates for a shift toward a granular, component-level understanding of their impacts. We propose TSCOMP, the first large-scale benchmark that systematically deconstructs deep forecasting methods into their core, fine-grained components--spanning series preprocessing, encoding strategies, network architectures including specific and large time-series models, and optimization methods. Using constrained orthogonal experimental design and extensive evaluations, we conduct multi-view analyses that reveal component effectiveness across different backbones, data characteristics, and their interactions. Beyond providing insights, this benchmark establishes a fine-grained performance corpus comprising over 20,000 model-dataset evaluations, which supports the learning of automated component selection, enabling zero-shot model construction on new datasets. Our experiments demonstrate that the corpus-driven approach, despite its simplicity, consistently outperforms state-of-the-art methods, validating the soundness of our evaluation design and confirming that systematic component selection surpasses manually designed complex architectures. All code and the performance corpus are publicly available at https://github.com/SUFE-AILAB/TSCOMP.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{liang2026beyond,
title = {Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting},
author = {Shuang Liang and Chaochuan Hou and Xu Yao and Shiping Wang and Hailiang Huang and Songqiao Han and Minqi Jiang},
year = {2026},
abstract = {While previous research in multivariate time series forecasting has focused on developing complex holistic models, this work advocates for a shift toward a granular, component-level understanding of their impacts. We propose TSCOMP, the first large-scale benchmark that systematically deconstructs deep forecasting methods into their core, fine-grained components--spanning series preprocessing, encoding strategies, network architectures including specific and large time-series models, and optimiza},
url = {https://huggingface.co/papers/2605.26562},
keywords = {multivariate time series forecasting, deep forecasting methods, component-level understanding, constrained orthogonal experimental design, multi-view analyses, automated component selection, zero-shot model construction, fine-grained components, series preprocessing, encoding strategies, network architectures, time-series models, optimization methods, code available, huggingface daily},
eprint = {2605.26562},
archiveprefix = {arXiv},
}
{}