{"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/ttms-fast-multi-level-tiny-time-mixers-for","title":"Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series","arxiv_id":"2401.03955","date":"2024-01-08","proceeding":null,"authors":["Vijay Ekambaram","Arindam Jati","Pankaj Dayama","Sumanta Mukherjee","Nam H. Nguyen","Wesley M. Gifford","Chandra Reddy","Jayant Kalagnanam"],"abstract":"Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characteristics. Consequently, recent research efforts have focused on developing pre-trained TS forecasting models. These models, whether built from scratch or adapted from large language models (LLMs), excel in zero/few-shot forecasting tasks. However, they are limited by slow performance, high computational demands, and neglect of cross-channel and exogenous correlations. To address this, we introduce Tiny Time Mixers (TTM), a compact model (starting from 1M parameters) with effective transfer learning capabilities, trained exclusively on public TS datasets. TTM, based on the light-weight TSMixer architecture, incorporates innovations like adaptive patching, diverse resolution sampling, and resolution prefix tuning to handle pre-training on varied dataset resolutions with minimal model capacity. Additionally, it employs multi-level modeling to capture channel correlations and infuse exogenous signals during fine-tuning. TTM outperforms existing popular benchmarks in zero/few-shot forecasting by (4-40%), while reducing computational requirements significantly. Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider adoption in resource-constrained environments. The model weights for reproducibility and research use are available at https://huggingface.co/ibm/ttm-research-r2/, while enterprise-use weights under the Apache license can be accessed as follows: the initial TTM-Q variant at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r1, and the latest variants (TTM-B, TTM-E, TTM-A) weights are available at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2.","url_abs":"https://arxiv.org/abs/2401.03955v8","url_pdf":"https://arxiv.org/pdf/2401.03955v8.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":[{"paper_slug":"ttms-fast-multi-level-tiny-time-mixers-for","repo_url":"https://github.com/ibm-granite/granite-tsfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"ttms-fast-multi-level-tiny-time-mixers-for","repo_url":"https://github.com/glehet/ttm1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"mlp-mixer","method_name":"MLP-Mixer"},{"method_slug":"mixer-layer","method_name":"Mixer Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"ts","method_name":"TS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/time-series-forecasting-on-etth1-96-1","task":"Time Series Forecasting","dataset":"ETTh1 (96) Multivariate","model":"TTM","rank_in_archive_order":6,"of":15,"metrics":{"MSE":"0.36"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.03955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03955"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibm-granite/granite-tsfm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/glehet/ttm1","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran_honours":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"4a545dae1d7f56c6","entry":"infer_phase_epochs","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a545dae1d7f56c6"}},{"code_sha256_prefix":"bb3d370e56564eef","entry":"model_cfg","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.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":"bb3d370e56564eef"}},{"code_sha256_prefix":"3f24fcf4f6794d81","entry":"nll","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f24fcf4f6794d81"}},{"code_sha256_prefix":"0743fdfa4cb9f3d3","entry":"trainable_params","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/notebooks/hfdemo/tinytimemixer/ttm_decomposed_pretrain_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0743fdfa4cb9f3d3"}},{"code_sha256_prefix":"974c725d14a0a9fc","entry":"update_patch_mask","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"974c725d14a0a9fc"}},{"code_sha256_prefix":"f240ef344beb6edd","entry":"weighted_l1_over_horizon","repo":"ibm-granite/granite-tsfm","repo_kind":"official","path":"tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","file_url":"https://github.com/ibm-granite/granite-tsfm/blob/HEAD/tsfm_public/models/tinytimemixer/modeling_tinytimemixer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f240ef344beb6edd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}