{"url":"/task/imputation","name":"Imputation","slug":"imputation","description_markdown":"Substituting missing data with values according to some criteria.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1237,"papers_with_code":479,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/imputation-on-adult-data-set","slug":"imputation-on-adult-data-set","dataset":"Adult","dataset_url":"/dataset/adult-data-set","rows_in_archive":1,"metrics":["Test error"],"first_row_in_archive_order":{"model":"ANN","paper_title":"Missing Data Imputation for Supervised Learning","paper_url":"/paper/missing-data-imputation-for-supervised","paper_date":"2016-10-28","arxiv_id":"1610.09075","code_links":[{"title":"rafaelvalle/MDI","url":"https://github.com/rafaelvalle/MDI"}],"syntology":null}},{"leaderboard":"/sota/imputation-on-hmnist","slug":"imputation-on-hmnist","dataset":"HMNIST","dataset_url":null,"rows_in_archive":1,"metrics":["AUROC","MSE","NLL"],"first_row_in_archive_order":{"model":"GP-VAE (B-NLST)","paper_title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","paper_url":"/paper/seq2tens-an-efficient-representation-of","paper_date":"2020-06-12","arxiv_id":"2006.07027","code_links":[{"title":"tgcsaba/seq2tens","url":"https://github.com/tgcsaba/seq2tens"}],"syntology":null}},{"leaderboard":"/sota/imputation-on-physionet-challenge-2012","slug":"imputation-on-physionet-challenge-2012","dataset":"PhysioNet Challenge 2012","dataset_url":"/dataset/physionet-challenge-2012","rows_in_archive":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"GP-VAE (B-NLST)","paper_title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","paper_url":"/paper/seq2tens-an-efficient-representation-of","paper_date":"2020-06-12","arxiv_id":"2006.07027","code_links":[{"title":"tgcsaba/seq2tens","url":"https://github.com/tgcsaba/seq2tens"}],"syntology":null}},{"leaderboard":"/sota/imputation-on-sprites","slug":"imputation-on-sprites","dataset":"Sprites","dataset_url":"/dataset/sprites","rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"GP-VAE (B-NLST)","paper_title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","paper_url":"/paper/seq2tens-an-efficient-representation-of","paper_date":"2020-06-12","arxiv_id":"2006.07027","code_links":[{"title":"tgcsaba/seq2tens","url":"https://github.com/tgcsaba/seq2tens"}],"syntology":null}}],"datasets":[{"url":"/dataset/webkb","name":"WebKB","full_name":"WebKB","num_papers_in_archive":113},{"url":"/dataset/adult-data-set","name":"Adult","full_name":"","num_papers_in_archive":56},{"url":"/dataset/sprites","name":"Sprites","full_name":"2D Video Game Character Sprites","num_papers_in_archive":52},{"url":"/dataset/motionsense","name":"MotionSense","full_name":null,"num_papers_in_archive":35},{"url":"/dataset/physionet-challenge-2012","name":"PhysioNet Challenge 2012","full_name":"PhysioNet Challenge 2012","num_papers_in_archive":23},{"url":"/dataset/ecoli","name":"Ecoli","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/fdf","name":"FDF","full_name":"Flickr Diverse Faces","num_papers_in_archive":6},{"url":"/dataset/utsd","name":"UTSD","full_name":"Unified Time Series Dataset","num_papers_in_archive":6},{"url":"/dataset/metr-la-point-missing","name":"METR-LA Point Missing","full_name":"","num_papers_in_archive":3},{"url":"/dataset/pems-bay-point-missing","name":"PEMS-BAY Point Missing","full_name":"","num_papers_in_archive":3},{"url":"/dataset/pulseimpute","name":"PulseImpute","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aids-antiviral-screen","name":"AIDS Antiviral Screen","full_name":"AIDS Antiviral Screen","num_papers_in_archive":1}],"subtasks":[{"url":"/task/multivariate-time-series-imputation","name":"Multivariate Time Series Imputation"}],"parent_tasks":[{"url":"/task/feature-engineering","name":"Feature Engineering"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":479,"tagged_in_all":1237,"items":[{"url":"/paper/gain-missing-data-imputation-using-generative","title":"GAIN: Missing Data Imputation using Generative Adversarial Nets","date":"2018-06-07","arxiv_id":"1806.02920","repositories_listed":8,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/recurrent-neural-networks-for-multivariate","title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values","date":"2016-06-06","arxiv_id":"1606.01865","repositories_listed":7,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/deep-learning-in-single-cell-analysis","title":"Deep Learning in Single-Cell Analysis","date":"2022-10-22","arxiv_id":"2210.12385","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/a-transformer-based-framework-for-1","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","date":"2020-10-06","arxiv_id":"2010.02803","repositories_listed":6,"syntology":{"n":32,"n_ran":5,"n_unverified":27,"n_pointer_only":2}},{"url":"/paper/unsupervised-data-imputation-via-variational","title":"Unsupervised Data Imputation via Variational Inference of Deep Subspaces","date":"2019-03-08","arxiv_id":"1903.03503","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/deep-learning-for-multivariate-time-series","title":"Deep Learning for Multivariate Time Series Imputation: A Survey","date":"2024-02-06","arxiv_id":"2402.04059","repositories_listed":5,"syntology":null},{"url":"/paper/generating-and-imputing-tabular-data-via","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","date":"2023-09-18","arxiv_id":"2309.09968","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pypots-a-python-toolbox-for-data-mining-on","title":"PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series","date":"2023-05-30","arxiv_id":"2305.18811","repositories_listed":5,"syntology":{"n":21,"n_ran":0,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/csdi-conditional-score-based-diffusion-models","title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","date":"2021-07-07","arxiv_id":"2107.03502","repositories_listed":5,"syntology":{"n":19,"n_ran":10,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/brits-bidirectional-recurrent-imputation-for","title":"BRITS: Bidirectional Recurrent Imputation for Time Series","date":"2018-05-27","arxiv_id":"1805.10572","repositories_listed":5,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/tsi-bench-benchmarking-time-series-imputation-1","title":"TSI-Bench: Benchmarking Time Series Imputation","date":"2024-06-18","arxiv_id":"2406.12747","repositories_listed":4,"syntology":null},{"url":"/paper/unity-by-diversity-improved-representation","title":"Unity by Diversity: Improved Representation Learning in Multimodal VAEs","date":"2024-03-08","arxiv_id":"2403.05300","repositories_listed":4,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/multivariate-time-series-imputation-with-1","title":"GP-VAE: Deep Probabilistic Time Series Imputation","date":"2019-07-09","arxiv_id":"1907.04155","repositories_listed":4,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/imaging-time-series-to-improve-classification","title":"Imaging Time-Series to Improve Classification and Imputation","date":"2015-06-01","arxiv_id":"1506.00327","repositories_listed":4,"syntology":null},{"url":"/paper/timesnet-temporal-2d-variation-modeling-for","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","date":"2022-10-05","arxiv_id":"2210.02186","repositories_listed":3,"syntology":null},{"url":"/paper/saits-self-attention-based-imputation-for","title":"SAITS: Self-Attention-based Imputation for Time Series","date":"2022-02-17","arxiv_id":"2202.08516","repositories_listed":3,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/geometry-and-accuracy-preserving-random","title":"Geometry- and Accuracy-Preserving Random Forest Proximities","date":"2022-01-29","arxiv_id":"2201.12682","repositories_listed":3,"syntology":null},{"url":"/paper/a-review-of-deep-learning-methods-for","title":"A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data","date":"2020-10-23","arxiv_id":"2010.12493","repositories_listed":3,"syntology":null},{"url":"/paper/lung-segmentation-from-chest-x-rays-using","title":"Lung Segmentation from Chest X-rays using Variational Data Imputation","date":"2020-05-20","arxiv_id":"2005.10052","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/bayesian-temporal-factorization-for","title":"Bayesian Temporal Factorization for Multidimensional Time Series Prediction","date":"2019-10-14","arxiv_id":"1910.06366","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-kalman-networks-factorized","title":"Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces","date":"2019-05-17","arxiv_id":"1905.07357","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/on-the-consistency-of-supervised-learning","title":"On the consistency of supervised learning with missing values","date":"2019-02-19","arxiv_id":"1902.06931","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/handling-incomplete-heterogeneous-data-using","title":"Handling Incomplete Heterogeneous Data using VAEs","date":"2018-07-10","arxiv_id":"1807.03653","repositories_listed":3,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/variational-autoencoder-with-arbitrary","title":"Variational Autoencoder with Arbitrary Conditioning","date":"2018-06-06","arxiv_id":"1806.02382","repositories_listed":3,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/mida-multiple-imputation-using-denoising","title":"MIDA: Multiple Imputation using Denoising Autoencoders","date":"2017-05-08","arxiv_id":"1705.02737","repositories_listed":3,"syntology":null},{"url":"/paper/input-convex-neural-networks","title":"Input Convex Neural Networks","date":"2016-09-22","arxiv_id":"1609.07152","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/peakweather-meteoswiss-weather-station","title":"PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning","date":"2025-06-16","arxiv_id":"2506.13652","repositories_listed":2,"syntology":null},{"url":"/paper/jolt-joint-probabilistic-predictions-on","title":"JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs","date":"2025-02-17","arxiv_id":"2502.11877","repositories_listed":2,"syntology":{"n":19,"n_ran":0,"n_unverified":19,"n_pointer_only":0}},{"url":"/paper/tabularargn-a-flexible-and-efficient-auto-1","title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","date":"2025-01-21","arxiv_id":"2501.12012","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/using-matrix-product-states-for-time-series","title":"Using matrix-product states for time-series machine learning","date":"2024-12-20","arxiv_id":"2412.15826","repositories_listed":2,"syntology":null}],"syntology_records":20,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}