Papers › Knowledge Distillation Based on Transformed Teacher Matching

Knowledge Distillation Based on Transformed Teacher Matching

17 Feb 2024arXiv:2402.11148archive 2025-07-28

Kaixiang Zheng, En-hui Yang

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.11148")

Code

Syntology Ran 5 of 7 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zkxufo/TTM officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
2ran
2unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zkxufo/TTM. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv3x3 zkxufo/TTM/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv_1x1_bn zkxufo/TTM/models/mobilenetv2.py official repository ran MIT (permissive) · 7765583b9e540679 · report
conv_bn zkxufo/TTM/models/mobilenetv2.py official repository ran · our draft was wrong MIT (permissive) · 2f7853ff01cbbc29 · report
get_teacher_name zkxufo/TTM/train_student.py official repository ran · our draft was wrong MIT (permissive) · 4b4f0463521302e8 · report
mobilenetv2_T_w zkxufo/TTM/models/mobilenetv2.py official repository ran MIT (permissive) · 421fd14c036bc279 · report
get_cifar100_dataloaders zkxufo/TTM/dataset/cifar100.py official repository unverified MIT (permissive) · 1928ecb540438f4e · report
get_cifar100_dataloaders_sample zkxufo/TTM/dataset/cifar100.py official repository unverified MIT (permissive) · 1a2603da723a67e9 · report

Tasks

Knowledge Distillation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Distillation ImageNet WTTM (T: DeiT III-Small S:DeiT-Tiny) CRD training setting ✘ #23 of 52 Archive leaderboard report
Knowledge Distillation ImageNet WTTM (T: DeiT III-Small S:DeiT-Tiny) Top-1 accuracy % 77.03 #23 of 52 Archive leaderboard report
Knowledge Distillation ImageNet WTTM (T:resnet50, S:mobilenet-v1) Top-1 accuracy % 73.09 #26 of 52 Archive leaderboard report
Knowledge Distillation ImageNet WTTM (T: ResNet-34 S:ResNet-18) CRD training setting ✓ #33 of 52 Archive leaderboard report
Knowledge Distillation ImageNet WTTM (T: ResNet-34 S:ResNet-18) Top-1 accuracy % 72.19 #33 of 52 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Knowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections