accepted by KDD 2026 Datasets and Benchmarks Track</p>\n","updatedAt":"2026-06-01T10:28:24.253Z","author":{"_id":"669162c4e3797743e86e8410","avatarUrl":"/avatars/c308ecbcd4fd6f1614ae061b3b37fea6.svg","fullname":"Chaochuan Hou","name":"Braudo","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8910253047943115},"editors":["Braudo"],"editorAvatarUrls":["/avatars/c308ecbcd4fd6f1614ae061b3b37fea6.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.26562","authors":[{"_id":"6a1d1c9a808ddbc3c7d43647","name":"Shuang Liang","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d43648","user":{"_id":"669162c4e3797743e86e8410","avatarUrl":"/avatars/c308ecbcd4fd6f1614ae061b3b37fea6.svg","isPro":false,"fullname":"Chaochuan Hou","user":"Braudo","type":"user","name":"Braudo"},"name":"Chaochuan Hou","status":"claimed_verified","statusLastChangedAt":"2026-06-01T09:32:13.996Z","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d43649","name":"Xu Yao","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d4364a","name":"Shiping Wang","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d4364b","name":"Hailiang Huang","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d4364c","name":"Songqiao Han","hidden":false},{"_id":"6a1d1c9a808ddbc3c7d4364d","name":"Minqi Jiang","hidden":false}],"publishedAt":"2026-05-26T00:00:00.000Z","submittedOnDailyAt":"2026-06-01T00:00:00.000Z","title":"Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting","submittedOnDailyBy":{"_id":"669162c4e3797743e86e8410","avatarUrl":"/avatars/c308ecbcd4fd6f1614ae061b3b37fea6.svg","isPro":false,"fullname":"Chaochuan Hou","user":"Braudo","type":"user","name":"Braudo"},"summary":"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.","upvotes":0,"discussionId":"6a1d1c9a808ddbc3c7d4364e","githubRepo":"https://github.com/SUFE-AILAB/TSCOMP","githubRepoAddedBy":"user","ai_summary":"A large-scale benchmark systematically decomposes deep forecasting methods into fine-grained components to enable automated model selection and outperform complex architectures.","ai_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"],"githubStars":17},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.26562.md"}">
Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting
Abstract
A large-scale benchmark systematically decomposes deep forecasting methods into fine-grained components to enable automated model selection and outperform complex architectures.
AI-generated summary
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.
Community
accepted by KDD 2026 Datasets and Benchmarks Track
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.26562 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.26562 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.26562 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.