{"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/brits-bidirectional-recurrent-imputation-for","title":"BRITS: Bidirectional Recurrent Imputation for Time Series","arxiv_id":"1805.10572","date":"2018-05-27","proceeding":"NeurIPS 2018 12","authors":["Wei Cao","Dong Wang","Jian Li","Hao Zhou","Lei LI","Yitan Li"],"abstract":"Time series are widely used as signals in many classification/regression\ntasks. It is ubiquitous that time series contains many missing values. Given\nmultiple correlated time series data, how to fill in missing values and to\npredict their class labels? Existing imputation methods often impose strong\nassumptions of the underlying data generating process, such as linear dynamics\nin the state space. In this paper, we propose BRITS, a novel method based on\nrecurrent neural networks for missing value imputation in time series data. Our\nproposed method directly learns the missing values in a bidirectional recurrent\ndynamical system, without any specific assumption. The imputed values are\ntreated as variables of RNN graph and can be effectively updated during the\nbackpropagation.BRITS has three advantages: (a) it can handle multiple\ncorrelated missing values in time series; (b) it generalizes to time series\nwith nonlinear dynamics underlying; (c) it provides a data-driven imputation\nprocedure and applies to general settings with missing data.We evaluate our\nmodel on three real-world datasets, including an air quality dataset, a\nhealth-care data, and a localization data for human activity. Experiments show\nthat our model outperforms the state-of-the-art methods in both imputation and\nclassification/regression accuracies.","url_abs":"http://arxiv.org/abs/1805.10572v1","url_pdf":"http://arxiv.org/pdf/1805.10572v1.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":"brits-bidirectional-recurrent-imputation-for","repo_url":"https://github.com/WenjieDu/PyPOTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"brits-bidirectional-recurrent-imputation-for","repo_url":"https://github.com/NIPS-BRITS/BRITS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"brits-bidirectional-recurrent-imputation-for","repo_url":"https://github.com/caow13/BRITS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"brits-bidirectional-recurrent-imputation-for","repo_url":"https://github.com/flaviagiammarino/brits-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"brits-bidirectional-recurrent-imputation-for","repo_url":"https://github.com/WenjieDu/SAITS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"missing-values","task_name":"Missing Values"},{"task_slug":"multivariate-time-series-forecasting","task_name":"Multivariate Time Series Forecasting"},{"task_slug":"multivariate-time-series-imputation","task_name":"Multivariate Time Series Imputation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"traffic-data-imputation","task_name":"Traffic Data Imputation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multivariate-time-series-forecasting-on-ushcn","task":"Multivariate Time Series Forecasting","dataset":"USHCN-Daily","model":"BRITS","rank_in_archive_order":4,"of":8,"metrics":{"MSE":"0.53"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on-2","task":"Multivariate Time Series Imputation","dataset":"Basketball Players Movement","model":"BRITS (SingleRes)","rank_in_archive_order":2,"of":5,"metrics":{"OOB Rate (10^−3) ":"3.874","Path Difference":"0.571","Path Length":"0.702","Player Distance ":"0.417","Step Change (10^−3)":"4.811"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on","task":"Multivariate Time Series Imputation","dataset":"Beijing Multi-Site Air-Quality Dataset","model":"BRITS","rank_in_archive_order":2,"of":6,"metrics":{"MAE (PM2.5)":"11.56"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on-pems","task":"Multivariate Time Series Imputation","dataset":"PEMS-SF","model":"BRITS (SingleRes)","rank_in_archive_order":2,"of":5,"metrics":{"L2 Loss (10^-4)":"4.51"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on-1","task":"Multivariate Time Series Imputation","dataset":"PhysioNet Challenge 2012","model":"BRITS","rank_in_archive_order":2,"of":9,"metrics":{"MAE (10% of data as GT)":"0.281"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on-uci","task":"Multivariate Time Series Imputation","dataset":"UCI localization data","model":"BRITS","rank_in_archive_order":1,"of":5,"metrics":{"MAE (10% missing)":"0.219"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-data-imputation-on-metr-la-point","task":"Traffic Data Imputation","dataset":"METR-LA Point Missing","model":"BRITS","rank_in_archive_order":2,"of":2,"metrics":{"MAE":"2.34"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-data-imputation-on-pems-bay-point","task":"Traffic Data Imputation","dataset":"PEMS-BAY Point Missing","model":"BRITS","rank_in_archive_order":2,"of":2,"metrics":{"MAE":"1.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.10572"}},"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/caow13/BRITS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NIPS-BRITS/BRITS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WenjieDu/SAITS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flaviagiammarino/brits-tensorflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WenjieDu/PyPOTS","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"named_in_paper":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":1,"ran":0,"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":"f63ba35d466f3c1f","entry":"parse_delta","repo":"caow13/BRITS","repo_kind":"named_in_paper","path":"input_process.py","file_url":"https://github.com/caow13/BRITS/blob/HEAD/input_process.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f63ba35d466f3c1f"}},{"code_sha256_prefix":"310bad2b2b34385d","entry":"to_time_bin","repo":"caow13/BRITS","repo_kind":"named_in_paper","path":"input_process.py","file_url":"https://github.com/caow13/BRITS/blob/HEAD/input_process.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"310bad2b2b34385d"}},{"code_sha256_prefix":"09da6e3827e4f7db","entry":"get_inputs","repo":"flaviagiammarino/brits-tensorflow","repo_kind":"listed","path":"brits_tensorflow/utils.py","file_url":"https://github.com/flaviagiammarino/brits-tensorflow/blob/HEAD/brits_tensorflow/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09da6e3827e4f7db"}},{"code_sha256_prefix":"1f69d0fb9551471c","entry":"parse_data","repo":"caow13/BRITS","repo_kind":"named_in_paper","path":"input_process.py","file_url":"https://github.com/caow13/BRITS/blob/HEAD/input_process.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f69d0fb9551471c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}