{"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/subspace-network-deep-multi-task-censored","title":"Subspace Network: Deep Multi-Task Censored Regression for Modeling Neurodegenerative Diseases","arxiv_id":"1802.06516","date":"2018-02-19","proceeding":"ICLR 2018 1","authors":["Mengying Sun","Inci M. Baytas","Liang Zhan","Zhangyang Wang","Jiayu Zhou"],"abstract":"Over the past decade a wide spectrum of machine learning models have been\ndeveloped to model the neurodegenerative diseases, associating biomarkers,\nespecially non-intrusive neuroimaging markers, with key clinical scores\nmeasuring the cognitive status of patients. Multi-task learning (MTL) has been\ncommonly utilized by these studies to address high dimensionality and small\ncohort size challenges. However, most existing MTL approaches are based on\nlinear models and suffer from two major limitations: 1) they cannot explicitly\nconsider upper/lower bounds in these clinical scores; 2) they lack the\ncapability to capture complicated non-linear interactions among the variables.\nIn this paper, we propose Subspace Network, an efficient deep modeling approach\nfor non-linear multi-task censored regression. Each layer of the subspace\nnetwork performs a multi-task censored regression to improve upon the\npredictions from the last layer via sketching a low-dimensional subspace to\nperform knowledge transfer among learning tasks. Under mild assumptions, for\neach layer the parametric subspace can be recovered using only one pass of\ntraining data. Empirical results demonstrate that the proposed subspace network\nquickly picks up the correct parameter subspaces, and outperforms\nstate-of-the-arts in predicting neurodegenerative clinical scores using\ninformation in brain imaging.","url_abs":"http://arxiv.org/abs/1802.06516v2","url_pdf":"http://arxiv.org/pdf/1802.06516v2.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":"subspace-network-deep-multi-task-censored","repo_url":"https://github.com/illidanlab/subspace-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.06516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06516"}},"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/illidanlab/subspace-net","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"717b4f5c0293e77f","entry":"algorithm_V","repo":"illidanlab/subspace-net","repo_kind":"official","path":"code/Exp1/Algorithm1.py","file_url":"https://github.com/illidanlab/subspace-net/blob/HEAD/code/Exp1/Algorithm1.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"717b4f5c0293e77f"}},{"code_sha256_prefix":"ece079e3119e1a71","entry":"calculate_loss","repo":"illidanlab/subspace-net","repo_kind":"official","path":"code/Exp1/Algorithm1.py","file_url":"https://github.com/illidanlab/subspace-net/blob/HEAD/code/Exp1/Algorithm1.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ece079e3119e1a71"}},{"code_sha256_prefix":"94c3efea4c665a86","entry":"safe_ln","repo":"illidanlab/subspace-net","repo_kind":"official","path":"code/Exp1/Algorithm1.py","file_url":"https://github.com/illidanlab/subspace-net/blob/HEAD/code/Exp1/Algorithm1.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"94c3efea4c665a86"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}