{"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/relational-knowledge-distillation","title":"Relational Knowledge Distillation","arxiv_id":"1904.05068","date":"2019-04-10","proceeding":"CVPR 2019 6","authors":["Wonpyo Park","Dongju Kim","Yan Lu","Minsu Cho"],"abstract":"Knowledge distillation aims at transferring knowledge acquired in one model\n(a teacher) to another model (a student) that is typically smaller. Previous\napproaches can be expressed as a form of training the student to mimic output\nactivations of individual data examples represented by the teacher. We\nintroduce a novel approach, dubbed relational knowledge distillation (RKD),\nthat transfers mutual relations of data examples instead. For concrete\nrealizations of RKD, we propose distance-wise and angle-wise distillation\nlosses that penalize structural differences in relations. Experiments conducted\non different tasks show that the proposed method improves educated student\nmodels with a significant margin. In particular for metric learning, it allows\nstudents to outperform their teachers' performance, achieving the state of the\narts on standard benchmark datasets.","url_abs":"http://arxiv.org/abs/1904.05068v2","url_pdf":"http://arxiv.org/pdf/1904.05068v2.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":"relational-knowledge-distillation","repo_url":"https://github.com/aquvitae/aquvitae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"relational-knowledge-distillation","repo_url":"https://github.com/lenscloth/RKD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"relational-knowledge-distillation","repo_url":"https://github.com/yoshitomo-matsubara/torchdistill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05068"}},"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/yoshitomo-matsubara/torchdistill","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lenscloth/RKD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aquvitae/aquvitae","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"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":1,"samples":[{"code_sha256_prefix":"a427a6169de8f607","entry":"compute_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a427a6169de8f607"}},{"code_sha256_prefix":"d14d058d883fceb0","entry":"dist","repo":"aquvitae/aquvitae","repo_kind":"listed","path":"aquvitae/dist.py","file_url":"https://github.com/aquvitae/aquvitae/blob/HEAD/aquvitae/dist.py","link_basis":"harvester_set","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":"d14d058d883fceb0"}},{"code_sha256_prefix":"523eadba66491517","entry":"result_to_tqdm_template","repo":"aquvitae/aquvitae","repo_kind":"listed","path":"aquvitae/utils.py","file_url":"https://github.com/aquvitae/aquvitae/blob/HEAD/aquvitae/utils.py","link_basis":"harvester_set","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":"523eadba66491517"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}