{"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/naomi-non-autoregressive-multiresolution","title":"NAOMI: Non-Autoregressive Multiresolution Sequence Imputation","arxiv_id":"1901.10946","date":"2019-01-30","proceeding":"NeurIPS 2019 12","authors":["Yukai Liu","Rose Yu","Stephan Zheng","Eric Zhan","Yisong Yue"],"abstract":"Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) to impute long-range sequences given arbitrary missing patterns. NAOMI exploits the multiresolution structure of spatiotemporal data and decodes recursively from coarse to fine-grained resolutions using a divide-and-conquer strategy. We further enhance our model with adversarial training. When evaluated extensively on benchmark datasets from systems of both deterministic and stochastic dynamics. NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization for long range sequences.","url_abs":"https://arxiv.org/abs/1901.10946v3","url_pdf":"https://arxiv.org/pdf/1901.10946v3.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":"naomi-non-autoregressive-multiresolution","repo_url":"https://github.com/felixykliu/NAOMI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"multivariate-time-series-imputation","task_name":"Multivariate Time Series Imputation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multivariate-time-series-imputation-on-2","task":"Multivariate Time Series Imputation","dataset":"Basketball Players Movement","model":"NAOMI","rank_in_archive_order":1,"of":5,"metrics":{"OOB Rate (10^−3) ":"1.733","Path Difference":"0.581","Path Length":"0.573","Player Distance ":"0.423","Step Change (10^−3)":"2.565"},"uses_additional_data":false},{"leaderboard":"/sota/multivariate-time-series-imputation-on-pems","task":"Multivariate Time Series Imputation","dataset":"PEMS-SF","model":"NAOMI","rank_in_archive_order":1,"of":5,"metrics":{"L2 Loss (10^-4)":"3.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.10946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10946"}},"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/felixykliu/NAOMI","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"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":"dcc2aedb4ca9a4e8","entry":"num_trainable_params","repo":"felixykliu/NAOMI","repo_kind":"official","path":"model.py","file_url":"https://github.com/felixykliu/NAOMI/blob/HEAD/model.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcc2aedb4ca9a4e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}