{"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/convtimenet-a-deep-hierarchical-fully","title":"ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis","arxiv_id":"2403.01493","date":"2024-03-03","proceeding":null,"authors":["Mingyue Cheng","Jiqian Yang","Tingyue Pan","Qi Liu","Zhi Li"],"abstract":"Designing effective models for learning time series representations is foundational for time series analysis. Many previous works have explored time series representation modeling approaches and have made progress in this area. Despite their effectiveness, they lack adaptive perception of local patterns in temporally dependent basic units and fail to capture the multi-scale dependency among these units. Instead of relying on prevalent methods centered around self-attention mechanisms, we propose ConvTimeNet, a hierarchical pure convolutional model designed for time series analysis. ConvTimeNet introduces a deformable patch layer that adaptively perceives local patterns of temporally dependent basic units in a data-driven manner. Based on the extracted local patterns, hierarchical pure convolutional blocks are designed to capture dependency relationships among the representations of basic units at different scales. Moreover, a large kernel mechanism is employed to ensure that convolutional blocks can be deeply stacked, thereby achieving a larger receptive field. In this way, local patterns and their multi-scale dependencies can be effectively modeled within a single model. Extensive experiments comparing a wide range of different types of models demonstrate that pure convolutional models still exhibit strong viability, effectively addressing the aforementioned two challenges and showing superior performance across multiple tasks. The code is available for reproducibility.","url_abs":"https://arxiv.org/abs/2403.01493v2","url_pdf":"https://arxiv.org/pdf/2403.01493v2.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":"convtimenet-a-deep-hierarchical-fully","repo_url":"https://github.com/mingyue-cheng/convtimenet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"convtimenet-a-deep-hierarchical-fully","repo_url":"https://github.com/mingyue-cheng/formertime","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"convtimenet-a-deep-hierarchical-fully","repo_url":"https://github.com/mingyue-cheng/timemae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/time-series-forecasting-on-etth1-336-1","task":"Time Series Forecasting","dataset":"ETTh1 (336) Multivariate","model":"ConvTimeNet","rank_in_archive_order":10,"of":72,"metrics":{"MAE":"0.420","MSE":"0.405"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.01493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01493"}},"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/mingyue-cheng/convtimenet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mingyue-cheng/timemae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mingyue-cheng/formertime","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"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":5,"samples":[{"code_sha256_prefix":"72b9272542f279c6","entry":"get_activation_fn","repo":"mingyue-cheng/convtimenet","repo_kind":"official","path":"TSForecasting/layers/ConvTimeNet_backbone.py","file_url":"https://github.com/mingyue-cheng/convtimenet/blob/HEAD/TSForecasting/layers/ConvTimeNet_backbone.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72b9272542f279c6"}},{"code_sha256_prefix":"5c170505ad8d13d2","entry":"get_activation_fn","repo":"mingyue-cheng/convtimenet","repo_kind":"official","path":"TSClassification/models/ConvTimeNet_backbone.py","file_url":"https://github.com/mingyue-cheng/convtimenet/blob/HEAD/TSClassification/models/ConvTimeNet_backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c170505ad8d13d2"}},{"code_sha256_prefix":"0caca29a79126837","entry":"normalize3","repo":"mingyue-cheng/convtimenet","repo_kind":"official","path":"TSClassification/preprocessed.py","file_url":"https://github.com/mingyue-cheng/convtimenet/blob/HEAD/TSClassification/preprocessed.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0caca29a79126837"}},{"code_sha256_prefix":"bdc787c888ab83a2","entry":"divide_no_nan","repo":"mingyue-cheng/convtimenet","repo_kind":"official","path":"TSClassification/utils/losses.py","file_url":"https://github.com/mingyue-cheng/convtimenet/blob/HEAD/TSClassification/utils/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdc787c888ab83a2"}},{"code_sha256_prefix":"de18456a7e019a9d","entry":"padding_varying_length","repo":"mingyue-cheng/convtimenet","repo_kind":"official","path":"TSClassification/preprocessed.py","file_url":"https://github.com/mingyue-cheng/convtimenet/blob/HEAD/TSClassification/preprocessed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de18456a7e019a9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}