{"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/hydra-preserving-ensemble-diversity-for-model-1","title":"Hydra: Preserving Ensemble Diversity for Model Distillation","arxiv_id":"2001.04694","date":"2020-01-14","proceeding":null,"authors":["Linh Tran","Bastiaan S. Veeling","Kevin Roth","Jakub Swiatkowski","Joshua V. Dillon","Jasper Snoek","Stephan Mandt","Tim Salimans","Sebastian Nowozin","Rodolphe Jenatton"],"abstract":"Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden of the ensemble while trying to preserve its predictive behavior. Most existing distillation formulations summarize the ensemble by capturing its average predictions. As a result, the diversity of the ensemble predictions, stemming from each member, is lost. Thus, the distilled model cannot provide a measure of uncertainty comparable to that of the original ensemble. To retain more faithfully the diversity of the ensemble, we propose a distillation method based on a single multi-headed neural network, which we refer to as Hydra. The shared body network learns a joint feature representation that enables each head to capture the predictive behavior of each ensemble member. We demonstrate that with a slight increase in parameter count, Hydra improves distillation performance on classification and regression settings while capturing the uncertainty behavior of the original ensemble over both in-domain and out-of-distribution tasks.","url_abs":"https://arxiv.org/abs/2001.04694v2","url_pdf":"https://arxiv.org/pdf/2001.04694v2.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":"hydra-preserving-ensemble-diversity-for-model-1","repo_url":"https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"hydra","method_name":"Hydra"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.04694","atlas_url":"https://app.syntology.ai/?focus=2001.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04694"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kaung-htet-myat/Multi-teachers-Knowledge-Distillation","reach":null}],"summary":{"ran_honours":1,"ran_fixture":2},"by_repo_kind":{"listed":{"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":"5c2990f3e8d448d1","entry":"resnet_layer","repo":"kaung-htet-myat/Multi-teachers-Knowledge-Distillation","repo_kind":"listed","path":"nets/student_model_multeacherKD.py","file_url":"https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation/blob/HEAD/nets/student_model_multeacherKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c2990f3e8d448d1"}},{"code_sha256_prefix":"b4fc1247b45aceb7","entry":"resnet_student","repo":"kaung-htet-myat/Multi-teachers-Knowledge-Distillation","repo_kind":"listed","path":"nets/student_model_multeacherKD.py","file_url":"https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation/blob/HEAD/nets/student_model_multeacherKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4fc1247b45aceb7"}},{"code_sha256_prefix":"e6aed85d8c334c9e","entry":"resnet_v1","repo":"kaung-htet-myat/Multi-teachers-Knowledge-Distillation","repo_kind":"listed","path":"nets/student_model_multeacherKD.py","file_url":"https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation/blob/HEAD/nets/student_model_multeacherKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6aed85d8c334c9e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}