{"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/wasserstein-distance-rivals-kullback-leibler","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","arxiv_id":"2412.08139","date":"2024-12-11","proceeding":null,"authors":["Jiaming Lv","Haoyuan Yang","Peihua Li"],"abstract":"Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and student while lacking a mechanism for cross-category comparison. Besides, KL-Div is problematic when applied to intermediate layers, as it cannot handle non-overlapping distributions and is unaware of geometry of the underlying manifold. To address these downsides, we propose a methodology of Wasserstein Distance (WD) based knowledge distillation. Specifically, we propose a logit distillation method called WKD-L based on discrete WD, which performs cross-category comparison of probabilities and thus can explicitly leverage rich interrelations among categories. Moreover, we introduce a feature distillation method called WKD-F, which uses a parametric method for modeling feature distributions and adopts continuous WD for transferring knowledge from intermediate layers. Comprehensive evaluations on image classification and object detection have shown (1) for logit distillation WKD-L outperforms very strong KL-Div variants; (2) for feature distillation WKD-F is superior to the KL-Div counterparts and state-of-the-art competitors. The source code is available at https://peihuali.org/WKD","url_abs":"https://arxiv.org/abs/2412.08139v1","url_pdf":"https://arxiv.org/pdf/2412.08139v1.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":"wasserstein-distance-rivals-kullback-leibler","repo_url":"https://github.com/JiamingLv/WKD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.08139","atlas_url":"https://app.syntology.ai/?focus=2412.08139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08139"}},"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/JiamingLv/WKD","reach":null}],"summary":{"ran":1,"ran_fixture":2,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"listed":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"a7d92810cbf3fd01","entry":"Distiller","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7d92810cbf3fd01"}},{"code_sha256_prefix":"0a86b2e40fe52f88","entry":"adaptive_avg_std_pool2d","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.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":"0a86b2e40fe52f88"}},{"code_sha256_prefix":"e6f1ae7024ada5d7","entry":"sinkhorn","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6f1ae7024ada5d7"}},{"code_sha256_prefix":"3be6ccd2a66c49ba","entry":"wkd_feature_loss","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3be6ccd2a66c49ba"}},{"code_sha256_prefix":"00973e6ddd35bda9","entry":"wkd_logit_loss","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00973e6ddd35bda9"}},{"code_sha256_prefix":"9c4310cf03bd30be","entry":"wkd_logit_loss_with_speration","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c4310cf03bd30be"}},{"code_sha256_prefix":"ae8a2a2f13729bbb","entry":"WKD","repo":"JiamingLv/WKD","repo_kind":"listed","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae8a2a2f13729bbb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}