{"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/unsupervised-data-imputation-via-variational","title":"Unsupervised Data Imputation via Variational Inference of Deep Subspaces","arxiv_id":"1903.03503","date":"2019-03-08","proceeding":null,"authors":["Adrian V. Dalca","John Guttag","Mert R. Sabuncu"],"abstract":"A wide range of systems exhibit high dimensional incomplete data. Accurate\nestimation of the missing data is often desired, and is crucial for many\ndownstream analyses. Many state-of-the-art recovery methods involve supervised\nlearning using datasets containing full observations. In contrast, we focus on\nunsupervised estimation of missing image data, where no full observations are\navailable - a common situation in practice. Unsupervised imputation methods for\nimages often employ a simple linear subspace to capture correlations between\ndata dimensions, omitting more complex relationships. In this work, we\nintroduce a general probabilistic model that describes sparse high dimensional\nimaging data as being generated by a deep non-linear embedding. We derive a\nlearning algorithm using a variational approximation based on convolutional\nneural networks and discuss its relationship to linear imputation models, the\nvariational auto encoder, and deep image priors. We introduce sparsity-aware\nnetwork building blocks that explicitly model observed and missing data. We\nanalyze proposed sparsity-aware network building blocks, evaluate our method on\npublic domain imaging datasets, and conclude by showing that our method enables\nimputation in an important real-world problem involving medical images. The\ncode is freely available as part of the \\verb|neuron| library at\nhttp://github.com/adalca/neuron.","url_abs":"http://arxiv.org/abs/1903.03503v1","url_pdf":"http://arxiv.org/pdf/1903.03503v1.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":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/adalca/neuron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/BBillot/SynthSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/BBillot/SynthSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/BBillot/hypothalamus_seg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/BBillot/lab2im","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unsupervised-data-imputation-via-variational","repo_url":"https://github.com/adalca/neurite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.03503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03503"}},"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/BBillot/hypothalamus_seg","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adalca/neurite","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BBillot/lab2im","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adalca/neuron","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BBillot/SynthSeg","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BBillot/SynthSR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"a4607bd51dd2ef63","entry":"flow","repo":"adalca/neuron","repo_kind":"official","path":"neurite/py/plot.py","file_url":"https://github.com/adalca/neuron/blob/HEAD/neurite/py/plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4607bd51dd2ef63"}},{"code_sha256_prefix":"31110973ca02ddb0","entry":"prior_to_weights","repo":"adalca/neuron","repo_kind":"official","path":"neurite/py/dataproc.py","file_url":"https://github.com/adalca/neuron/blob/HEAD/neurite/py/dataproc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31110973ca02ddb0"}},{"code_sha256_prefix":"2c02711440b8b56a","entry":"slices","repo":"adalca/neuron","repo_kind":"official","path":"neurite/py/plot.py","file_url":"https://github.com/adalca/neuron/blob/HEAD/neurite/py/plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c02711440b8b56a"}},{"code_sha256_prefix":"b578a1d36f2dab7a","entry":"softmax","repo":"adalca/neuron","repo_kind":"official","path":"neurite/py/utils.py","file_url":"https://github.com/adalca/neuron/blob/HEAD/neurite/py/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b578a1d36f2dab7a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}