{"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/t-cgan-conditional-generative-adversarial","title":"T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling","arxiv_id":"1811.08295","date":"2018-11-20","proceeding":null,"authors":["Giorgia Ramponi","Pavlos Protopapas","Marco Brambilla","Ryan Janssen"],"abstract":"In this paper we propose a data augmentation method for time series with\nirregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN).\nOur approach is based on Conditional Generative Adversarial Networks (CGAN),\nwhere the generative step is implemented by a deconvolutional NN and the\ndiscriminative step by a convolutional NN. Both the generator and the\ndiscriminator are conditioned on the sampling timestamps, to learn the hidden\nrelationship between data and timestamps, and consequently to generate new time\nseries. We evaluate our model with synthetic and real-world datasets. For the\nsynthetic data, we compare the performance of a classifier trained with\nT-CGAN-generated data, against the performance of the same classifier trained\non the original data. Results show that classifiers trained on T-CGAN-generated\ndata perform the same as classifiers trained on real data, even with very short\ntime series and small training sets. For the real world datasets, we compare\nour method with other techniques of data augmentation for time series, such as\ntime slicing and time warping, over a classification problem with unbalanced\ndatasets. Results show that our method always outperforms the other approaches,\nboth in case of regularly sampled and irregularly sampled time series. We\nachieve particularly good performance in case with a small training set and\nshort, noisy, irregularly-sampled time series.","url_abs":"http://arxiv.org/abs/1811.08295v2","url_pdf":"http://arxiv.org/pdf/1811.08295v2.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":"t-cgan-conditional-generative-adversarial","repo_url":"https://github.com/gioramponi/GAN_Time_Series","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"t-cgan-conditional-generative-adversarial","repo_url":"https://github.com/2023-MindSpore-1/ms-code-6/tree/main/CGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08295"}},"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/2023-MindSpore-1/ms-code-6/tree/main/CGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gioramponi/GAN_Time_Series","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"6483789993382daf","entry":"sample_curves","repo":"gioramponi/GAN_Time_Series","repo_kind":"listed","path":"experiments/routine_earth.py","file_url":"https://github.com/gioramponi/GAN_Time_Series/blob/HEAD/experiments/routine_earth.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6483789993382daf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}