{"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/parametric-augmentation-for-time-series","title":"Parametric Augmentation for Time Series Contrastive Learning","arxiv_id":"2402.10434","date":"2024-02-16","proceeding":null,"authors":["Xu Zheng","Tianchun Wang","Wei Cheng","Aitian Ma","Haifeng Chen","Mo Sha","Dongsheng Luo"],"abstract":"Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in learning robust and discriminative representations is a crucial stage in contrastive learning approaches. Usually, preset human intuition directs the selection of relevant data augmentations. Due to patterns that are easily recognized by humans, this rule of thumb works well in the vision and language domains. However, it is impractical to visually inspect the temporal structures in time series. The diversity of time series augmentations at both the dataset and instance levels makes it difficult to choose meaningful augmentations on the fly. In this study, we address this gap by analyzing time series data augmentation using information theory and summarizing the most commonly adopted augmentations in a unified format. We then propose a contrastive learning framework with parametric augmentation, AutoTCL, which can be adaptively employed to support time series representation learning. The proposed approach is encoder-agnostic, allowing it to be seamlessly integrated with different backbone encoders. Experiments on univariate forecasting tasks demonstrate the highly competitive results of our method, with an average 6.5\\% reduction in MSE and 4.7\\% in MAE over the leading baselines. In classification tasks, AutoTCL achieves a $1.2\\%$ increase in average accuracy.","url_abs":"https://arxiv.org/abs/2402.10434v1","url_pdf":"https://arxiv.org/pdf/2402.10434v1.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":"parametric-augmentation-for-time-series","repo_url":"https://github.com/AslanDing/AutoTCL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"time-series-1","task_name":"Time Series"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.10434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10434"}},"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/AslanDing/AutoTCL","reach":null}],"summary":{"ran_violates":4,"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"2f082023cfc91428","entry":"generate_binomial_mask","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"models/encoder.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/models/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f082023cfc91428"}},{"code_sha256_prefix":"46665cbab281b984","entry":"ConvBlock","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46665cbab281b984"}},{"code_sha256_prefix":"9bae7ac21b0b4465","entry":"DilatedConvEncoder","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9bae7ac21b0b4465"}},{"code_sha256_prefix":"dfd9d437685e03a0","entry":"SamePadConv","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfd9d437685e03a0"}},{"code_sha256_prefix":"fd10054ec4772b80","entry":"generate_binomial_mask","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fd10054ec4772b80"}},{"code_sha256_prefix":"6ac0ae7a5e51b013","entry":"generate_continuous_mask","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"models/encoder.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/models/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ac0ae7a5e51b013"}},{"code_sha256_prefix":"acda587a1d1be3bf","entry":"generate_continuous_mask","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"acda587a1d1be3bf"}},{"code_sha256_prefix":"dd5e264721a171a0","entry":"AutoTCL","repo":"AslanDing/AutoTCL","repo_kind":"official","path":"AutoTCL_CoST.py","file_url":"https://github.com/AslanDing/AutoTCL/blob/HEAD/AutoTCL_CoST.py","link_basis":"first_harvest_node","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":"dd5e264721a171a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}