{"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/dynamic-feature-acquisition-using-denoising","title":"Dynamic Feature Acquisition Using Denoising Autoencoders","arxiv_id":"1811.01249","date":"2018-11-03","proceeding":null,"authors":["Mohammad Kachuee","Sajad Darabi","Babak Moatamed","Majid Sarrafzadeh"],"abstract":"In real-world scenarios, different features have different acquisition costs\nat test-time which necessitates cost-aware methods to optimize the cost and\nperformance trade-off. This paper introduces a novel and scalable approach for\ncost-aware feature acquisition at test-time. The method incrementally asks for\nfeatures based on the available context that are known feature values. The\nproposed method is based on sensitivity analysis in neural networks and density\nestimation using denoising autoencoders with binary representation layers. In\nthe proposed architecture, a denoising autoencoder is used to handle unknown\nfeatures (i.e., features that are yet to be acquired), and the sensitivity of\npredictions with respect to each unknown feature is used as a context-dependent\nmeasure of informativeness. We evaluated the proposed method on eight different\nreal-world datasets as well as one synthesized dataset and compared its\nperformance with several other approaches in the literature. According to the\nresults, the suggested method is capable of efficiently acquiring features at\ntest-time in a cost- and context-aware fashion.","url_abs":"http://arxiv.org/abs/1811.01249v1","url_pdf":"http://arxiv.org/pdf/1811.01249v1.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":"dynamic-feature-acquisition-using-denoising","repo_url":"https://github.com/mkachuee/DynamicFeatureAcquisition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.01249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01249"}},"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/mkachuee/DynamicFeatureAcquisition","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"c00f4cf7deecc03d","entry":"feed_data","repo":"mkachuee/DynamicFeatureAcquisition","repo_kind":"listed","path":"src/nn_training.py","file_url":"https://github.com/mkachuee/DynamicFeatureAcquisition/blob/HEAD/src/nn_training.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":"c00f4cf7deecc03d"}},{"code_sha256_prefix":"66ed61e16b8fc1f1","entry":"feed_data_nhanes","repo":"mkachuee/DynamicFeatureAcquisition","repo_kind":"listed","path":"src/nn_training.py","file_url":"https://github.com/mkachuee/DynamicFeatureAcquisition/blob/HEAD/src/nn_training.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":"66ed61e16b8fc1f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}