{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/less-is-more-unlocking-specialization-of-time","title":"Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning","arxiv_id":"2505.23195","date":"2025-05-29","proceeding":null,"authors":["Lifan Zhao","Yanyan Shen","Zhaoyang Liu","Xue Wang","Jiaji Deng"],"abstract":"Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently outperform smaller, specialized models trained on full-shot downstream data. A key question is how to realize effective adaptation of TSFMs for a target forecasting task. Through empirical studies on various TSFMs, the pre-trained models often exhibit inherent sparsity and redundancy in computation, suggesting that TSFMs have learned to activate task-relevant network substructures to accommodate diverse forecasting tasks. To preserve this valuable prior knowledge, we propose a structured pruning method to regularize the subsequent fine-tuning process by focusing it on a more relevant and compact parameter space. Extensive experiments on seven TSFMs and six benchmarks demonstrate that fine-tuning a smaller, pruned TSFM significantly improves forecasting performance compared to fine-tuning original models. This \"prune-then-finetune\" paradigm often enables TSFMs to achieve state-of-the-art performance and surpass strong specialized baselines.","url_abs":"https://arxiv.org/abs/2505.23195v1","url_pdf":"https://arxiv.org/pdf/2505.23195v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.23195","atlas_url":"https://app.syntology.ai/?focus=2505.23195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23195"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/SJTU-DMTai/Prune-then-Finetune","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":5,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"92baea6ddfe32892","entry":"Mask","repo":"SJTU-DMTai/Prune-then-Finetune","repo_kind":"found_in_text","path":"src/tsfm/layers/prune_mask.py","file_url":"https://github.com/SJTU-DMTai/Prune-then-Finetune/blob/HEAD/src/tsfm/layers/prune_mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"92baea6ddfe32892"}},{"code_sha256_prefix":"efa644f09fe16714","entry":"accumulate_fisher","repo":"SJTU-DMTai/Prune-then-Finetune","repo_kind":"found_in_text","path":"src/tsfm/layers/prune_mask.py","file_url":"https://github.com/SJTU-DMTai/Prune-then-Finetune/blob/HEAD/src/tsfm/layers/prune_mask.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"efa644f09fe16714"}},{"code_sha256_prefix":"f0c01ac22ec18298","entry":"zero_tensor","repo":"SJTU-DMTai/Prune-then-Finetune","repo_kind":"found_in_text","path":"src/tsfm/layers/prune_mask.py","file_url":"https://github.com/SJTU-DMTai/Prune-then-Finetune/blob/HEAD/src/tsfm/layers/prune_mask.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0c01ac22ec18298"}},{"code_sha256_prefix":"4ea419fd7112b240","entry":"MaskedLayer","repo":"SJTU-DMTai/Prune-then-Finetune","repo_kind":"found_in_text","path":"src/tsfm/layers/prune_mask.py","file_url":"https://github.com/SJTU-DMTai/Prune-then-Finetune/blob/HEAD/src/tsfm/layers/prune_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ea419fd7112b240"}},{"code_sha256_prefix":"50f1a80d0df9c681","entry":"as_buffer_","repo":"SJTU-DMTai/Prune-then-Finetune","repo_kind":"found_in_text","path":"src/tsfm/layers/prune_mask.py","file_url":"https://github.com/SJTU-DMTai/Prune-then-Finetune/blob/HEAD/src/tsfm/layers/prune_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50f1a80d0df9c681"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}