{"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/knowledge-distillation-based-on-transformed","title":"Knowledge Distillation Based on Transformed Teacher Matching","arxiv_id":"2402.11148","date":"2024-02-17","proceeding":null,"authors":["Kaixiang Zheng","En-hui Yang"],"abstract":"As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature scaling is applied to both teacher's logits and student's logits in KD. Motivated by some recent works, in this paper, we drop instead temperature scaling on the student side, and systematically study the resulting variant of KD, dubbed transformed teacher matching (TTM). By reinterpreting temperature scaling as a power transform of probability distribution, we show that in comparison with the original KD, TTM has an inherent R\\'enyi entropy term in its objective function, which serves as an extra regularization term. Extensive experiment results demonstrate that thanks to this inherent regularization, TTM leads to trained students with better generalization than the original KD. To further enhance student's capability to match teacher's power transformed probability distribution, we introduce a sample-adaptive weighting coefficient into TTM, yielding a novel distillation approach dubbed weighted TTM (WTTM). It is shown, by comprehensive experiments, that although WTTM is simple, it is effective, improves upon TTM, and achieves state-of-the-art accuracy performance. Our source code is available at https://github.com/zkxufo/TTM.","url_abs":"https://arxiv.org/abs/2402.11148v2","url_pdf":"https://arxiv.org/pdf/2402.11148v2.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":"knowledge-distillation-based-on-transformed","repo_url":"https://github.com/zkxufo/TTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-distillation-on-imagenet","task":"Knowledge Distillation","dataset":"ImageNet","model":"WTTM (T: DeiT III-Small S:DeiT-Tiny)","rank_in_archive_order":23,"of":52,"metrics":{"CRD training setting":"✘","Top-1 accuracy %":"77.03"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-distillation-on-imagenet","task":"Knowledge Distillation","dataset":"ImageNet","model":"WTTM (T:resnet50, S:mobilenet-v1)","rank_in_archive_order":26,"of":52,"metrics":{"Top-1 accuracy %":"73.09"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-distillation-on-imagenet","task":"Knowledge Distillation","dataset":"ImageNet","model":"WTTM (T: ResNet-34 S:ResNet-18)","rank_in_archive_order":33,"of":52,"metrics":{"CRD training setting":"✓","Top-1 accuracy %":"72.19"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11148"}},"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":"deterministic:regex_extraction","url":"https://github.com/zkxufo/TTM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"zkxufo/TTM","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"7765583b9e540679","entry":"conv_1x1_bn","repo":"zkxufo/TTM","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/models/mobilenetv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7765583b9e540679"}},{"code_sha256_prefix":"2f7853ff01cbbc29","entry":"conv_bn","repo":"zkxufo/TTM","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/models/mobilenetv2.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f7853ff01cbbc29"}},{"code_sha256_prefix":"4b4f0463521302e8","entry":"get_teacher_name","repo":"zkxufo/TTM","repo_kind":"official","path":"train_student.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/train_student.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b4f0463521302e8"}},{"code_sha256_prefix":"421fd14c036bc279","entry":"mobilenetv2_T_w","repo":"zkxufo/TTM","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/models/mobilenetv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"421fd14c036bc279"}},{"code_sha256_prefix":"1928ecb540438f4e","entry":"get_cifar100_dataloaders","repo":"zkxufo/TTM","repo_kind":"official","path":"dataset/cifar100.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/dataset/cifar100.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":"1928ecb540438f4e"}},{"code_sha256_prefix":"1a2603da723a67e9","entry":"get_cifar100_dataloaders_sample","repo":"zkxufo/TTM","repo_kind":"official","path":"dataset/cifar100.py","file_url":"https://github.com/zkxufo/TTM/blob/HEAD/dataset/cifar100.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":"1a2603da723a67e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}