Papers › Distilling the Knowledge in a Neural Network

Distilling the Knowledge in a Neural Network

9 Mar 2015arXiv:1503.02531archive 2025-07-28

Geoffrey Hinton, Oriol Vinyals, Jeff Dean

A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 37 code samples: 36 from 14 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 37: 23 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 36 samples from 14 repositories, 23 ran (14 with no instrument failure; 9 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 13 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

64 repositories listed; official and paper-mentioned ones first.

Adlik/model_optimizer mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Ensemble Knowledge Distillation for Learning Improved and Efficient Networks (arXiv:1909.08097; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
DunZhang/KnowledgeDistillation mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
Irtza/Keras_model_compression mentioned on GitHubSyntology: not harvested report
JunzWu/Distilling-the-Knowledge-in-a-Neural-Network mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
KaiyuYue/mgd mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
KellyYutongHe/Knowledge-Distillation-Net-with-Swish mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
MasLiang/Learning-without-Forgetting-using-Pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MinJunKang/CIFAR-100--Knowledge-Distillation-with-Augmented-Data mentioned on GitHubtfSyntology: not harvested report
MinJunKang/ImageNet-Knowledge-Distillation mentioned on GitHubtfSyntology: not harvested report
MinJunKang/Knowledge-Distillation_MNIST mentioned on GitHubtfSyntology: not harvested report
NeelayS/Knowledge-Distillation mentioned on GitHubpytorchSyntology: not harvested report
TakieddineSOUALHI/Transfer_learning mentioned on GitHubSyntology: not harvested report
altndrr/persona mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FaceNet: A Unified Embedding for Face Recognition and Clustering (arXiv:1503.03832; that paper's own run record: 99 ran (of which 19 constructed an object rather than computing a result; 83 with no instrument failure: 11 honoured, 11 violated, 61 with no contract checked; 16 where Syntology's instrument failed) · 55 unverified); nothing checks that they implement this paper's method. report
ankur-98/Multi-domain-Knowledge-Distillation mentioned on GitHubpytorchSyntology: not harvested report
aquvitae/aquvitae mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Relational Knowledge Distillation (arXiv:1904.05068; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
aryanasadianuoit/distillation_deep mentioned on GitHubtfSyntology: not harvested report
chumingqian/Model_Compression_For_YOLOV3-V4 mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
elasticdeeplearning/edl mentioned on GitHubpaddleApache-2.0Syntology: not harvested report
franknb/Text-Summarization mentioned on GitHubSyntology: not harvested report
generation21/generation6011 mentioned on GitHubpytorchSyntology: not harvested report
haro-cyber/KnowledgeDistillation mentioned on GitHubtfSyntology: not harvested report
haysacks/spot-the-coin mentioned on GitHubtfSyntology: not harvested report
hunto/image_classification_sota mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diverse Branch Block: Building a Convolution as an Inception-like Unit (arXiv:2103.13425; that paper's own run record: 11 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified) and Knowledge Distillation from A Stronger Teacher (arXiv:2205.10536; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 4 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jaychoi12/LG_KD mentioned on GitHubpytorchSyntology: not harvested report
jchen98/compression mentioned on GitHubtfSyntology: not harvested report
jpmcd/TensorFlow-KnowledgeDistillation mentioned on GitHubtfSyntology: not harvested report
kaiyangzhou/on-device-dg mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
kaung-htet-myat/Multi-teachers-Knowledge-Distillation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hydra: Preserving Ensemble Diversity for Model Distillation (arXiv:2001.04694; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
knotgrass/Knowledge-Distillation mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
lingyucai/Distilling-the-Knowledge-in-a-Neural-Network mentioned on GitHubpytorchSyntology: not harvested report
markliou/model_distillation mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Probability density distillation with generative adversarial networks for high-quality... (arXiv:1904.04472; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
mckunkel/DistillingObjectDetector mentioned on GitHubMITSyntology: 9 samples, 1 ran (0 instrument-failed) · 8 unverified report
mkavim/finetune_bert mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified) and DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (arXiv:1910.01108; that paper's own run record: 21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
paddlepaddle/edl mentioned on GitHubpaddleApache-2.0Syntology: not harvested report
pra-dan/Worth-Reading-ML-Papers mentioned on GitHubSyntology: not harvested report
robertjkeck2/EmoNet mentioned on GitHubSyntology: not harvested report
robertjkeck2/EmoTe mentioned on GitHubSyntology: not harvested report
robertjkeck2/pwdl mentioned on GitHubSyntology: not harvested report
rohin-dasari/Tensorflow-Knowledge-Distillation mentioned on GitHubtfSyntology: not harvested report
satyakees/FaultNet mentioned on GitHubpytorchSyntology: not harvested report
scy-x/d3still mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
see--/speech_recognition mentioned on GitHubtfSyntology: not harvested report
shinome551/select_with_distillation mentioned on GitHubpytorchSyntology: not harvested report
shriramsb/Distilling-the-Knowledge-in-a-Neural-Network mentioned on GitHubpytorchSyntology: not harvested report
stdereka/knowledge-distillation mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
sungnyun/LG-knowledge-distillation mentioned on GitHubpytorchSyntology: not harvested report
t0nyliang/EEGMobile mentioned on GitHubpytorchSyntology: not harvested report
thaonguyen19/modeldistillation-pytorch mentioned on GitHubpytorchSyntology: not harvested report
trqminh/knowledge-distillation mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
varungumma/fairseq mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoFormer: Enhanced Transformer with Rotary Position Embedding (arXiv:2104.09864; that paper's own run record: 14 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
vrvlive/knowlege-distillation mentioned on GitHubpytorchSyntology: not harvested report
wannabeOG/ExpertNet-Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning without Forgetting (arXiv:1606.09282; that paper's own run record: 9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
wonbeomjang/Knowledge-Distilling-PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yangze01/Distilling_the_Knowledge_in_a_Neural_Network mentioned on GitHubpytorchSyntology: not harvested report
yangze01/Distilling_the_Knowledge_in_a_Neural_Network_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
yell/kaggle-camera mentioned on GitHubpytorchMITSyntology: not harvested report
yoshitomo-matsubara/torchdistill mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yurangja99/Pytorch-Sketch-RNN mentioned on GitHubpytorchSyntology: not harvested report
yzd-v/cls_KD mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
zh320/realtime-semantic-segmentation-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CGNet: A Light-weight Context Guided Network for Semantic Segmentation (arXiv:1811.08201; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network (arXiv:1811.11431; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified), Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Deci-AI/super-gradients pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified), RepVGG: Making VGG-style ConvNets Great Again (arXiv:2101.03697; that paper's own run record: 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
alibaba/EasyNLP jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural... (arXiv:2311.06761; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Adam: A Method for Stochastic Optimization (arXiv:1412.6980; that paper's own run record: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified), Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified) and 12 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
yangyucheng000/Papers mindsporeSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

37 samples harvested: 23 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · honoured contract
8ran · our draft was wrong
1ran; the contract check could not run
8ran
14unverified

Licence: 11 of the 37 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 14 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

DunZhang/KnowledgeDistillation community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
output_adaptor Examples/example_multi_layer_based_model/distill_bert.py ran · our draft was wrong licence not identified · pointer only · 0bd196791b1b86e6 · report fixture: signature model_output:tuple/1/Tensor · returned dict · level recorded 2026-09-22
train_data_adaptor Examples/example_multi_layer_based_model/distill_bert.py ran · our draft was wrong licence not identified · pointer only · 95712f5d0bd66d34 · report fixture: signature device:device/0/?, batch_data:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
JunzWu/Distilling-the-Knowledge-in-a-Neural-Network community (archive-listed) 1 sample, 0 ran · 1 unverified
validate in 313 papers main_imagenet.py unverified no licence file found · pointer only · 5b365f68a2be17aa · report
KaiyuYue/mgd community (archive-listed) 1 sample, 0 ran · 1 unverified
validate in 313 papers cls/main_mgd.py unverified MIT (permissive) · 41bcf9c6e97f30d5 · report
KellyYutongHe/Knowledge-Distillation-Net-with-Swish community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
fetch_teacher_outputs kd.py ran · honoured contract no licence file found · pointer only · 7ee88cf415894459 · report fixture: signature teacher_model:callable/0/?, dataloader:list/1/tuple · returned list · level recorded 2026-09-22
loss_fn_kd in 9 papers kd.py ran · our draft was wrong no licence file found · pointer only · 8a5635108617215c · report fixture: signature outputs:Tensor/2/float, labels:Tensor/1/int, teacher_outputs:Tensor/2/float, params:Params/0/? · returned Tensor · level recorded 2026-09-22
MasLiang/Learning-without-Forgetting-using-Pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
compute_mean_and_std dataset.py ran · honoured contract no licence file found · pointer only · 2cbf06e40dbf54ee · report fixture: signature dataset:MockDataset/0/? · returned tuple · level recorded 2026-09-22
chumingqian/Model_Compression_For_YOLOV3-V4 community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
obtain_avg_forward_time normal_prune.py ran · our draft was wrong Apache-2.0 (permissive) · 9c20329610d8c5e5 · report fixture: signature input:Tensor/2/float, model:callable/0/?, repeat:int/0/int · returned tuple · level recorded 2026-09-22
obtain_filters_mask normal_prune.py ran · our draft was wrong Apache-2.0 (permissive) · acb7b29614f1a161 · report fixture: signature model:callable/0/?, thre:float/0/float, CBL_idx:list/1/int, prune_idx:list/1/int · returned tuple · level recorded 2026-09-22
prune_and_eval normal_prune.py ran · our draft was wrong Apache-2.0 (permissive) · ec78bec91ac01396 · report fixture: signature model:callable/0/?, sorted_bn:Tensor/1/float, percent:float/0/float · returned Tensor · level recorded 2026-09-22
knotgrass/Knowledge-Distillation community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
albumen_loader distiller/datasets.py ran MIT (permissive) · 77551a1423d80be3 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-26
check_same_order distiller/sorted_same_order.py ran MIT (permissive) · 00c0d849e940be32 · report fixture: signature num1:list/1/int, num2:list/1/int · returned bool · level recorded 2026-09-26
desc distiller/print_utils.py ran MIT (permissive) · 671c7f056497a8b6 · report fixture: signature epoch:int/0/int, n_epoch:int/0/int, phase:str/0/str, loss:float/0/float, acc:float/0/float · returned str · level recorded 2026-09-26
get_order distiller/sorted_same_order.py ran MIT (permissive) · a8b17275da494ca9 · report fixture: signature nums:list/1/float · returned list · level recorded 2026-09-26
loss_fn_kd in 9 papers distiller/loss.py ran MIT (permissive) · 240a91c16bc48dd5 · report fixture: signature preds:Tensor/2/float, labels:Tensor/1/int, teacher_preds:Tensor/2/float, T:float/0/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-26
mean_std in 12 papers distiller/pseudo_label.py ran MIT (permissive) · 9f00b79fbcd75706 · report fixture: signature x:Tensor/1/float · returned tuple · level recorded 2026-09-26
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket this sample: bucket 1 of 8, arg 1: rank 2, kind float, dtype float32
distiller/loss.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · cb5cbea0e8219ff5 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22
sort_by_order distiller/sorted_same_order.py ran fingerprinted MIT (permissive) · 37db7f404db2f6ab · report fixture: signature nums1:list/1/int, nums2:list/1/int · returned list · level recorded 2026-09-26
train in 522 papers distiller/distiller.py unverified MIT (permissive) · f7005e3d307e1c00 · report
mckunkel/DistillingObjectDetector community (archive-listed) 9 samples, 1 ran (0 instrument-failed) · 8 unverified
preprocess_input in 26 papers models/microxception.py ran fingerprinted MIT (permissive) · bee766c6e15044c2 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SqueezeNet models/squeezenet.py unverified MIT (permissive) · f0854de100bbea76 · report
SqueezeNet models/squeezenet_model.py unverified MIT (permissive) · 6300eb91406d21bf · report
conv2d_bn in 12 papers models/inceptionV3.py unverified MIT (permissive) · f14f766b7e289b16 · report
fire_module models/squeezenet.py unverified MIT (permissive) · 1b249ba85d8cf4ba · report
get_mobilenet in 7 papers models/mobilenet.py unverified MIT (permissive) · 978081881d93f4be · report
microXception models/microxception.py unverified MIT (permissive) · 2d50b69c5762cfbe · report
miniXception models/minixception.py unverified MIT (permissive) · 3ec85b13b3da58a4 · report
preprocess_input in 26 papers models/squeezenet.py unverified MIT (permissive) · 9eb8ac7c03e9b11b · report
scy-x/d3still community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
d3_loss AIR_Distiller/distillers/D3.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 274528b19a06a729 · report fixture: signature student_features:Tensor/2/float, teacher_features:Tensor/2/float, topk:int/0/int, alpha:float/0/float, beta:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-22
stdereka/knowledge-distillation community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
eval_epoch in 13 papers training.py ran · honoured contract MIT (permissive) · 7308ca9b35a3b212 · report fixture: signature model:callable/0/?, val_loader:DataLoader/0/?, criterion:callable/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
fit_epoch training.py ran · honoured contract MIT (permissive) · 62f639fec5cb08e5 · report fixture: signature model:callable/0/?, train_loader:DataLoader/0/?, criterion:callable/0/?, optimizer:SGD/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
train in 522 papers training.py ran · honoured contract MIT (permissive) · 00a58257f6886584 · report fixture: signature train_dataset:SimpleDataset/0/?, val_dataset:SimpleDataset/0/?, model:callable/0/?, epochs:int/0/int, batch_size:int/0/int, device:str/0/str, opt:Adam/0/?, criterion:callable/0/? · returned ndarray · level recorded 2026-09-22
trqminh/knowledge-distillation community (archive-listed) 1 sample, 0 ran · 1 unverified
train_student_model train/train_student.py unverified no licence file found · pointer only · b7e8ebfd9b3a5233 · report
wonbeomjang/Knowledge-Distilling-PyTorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv_block in 95 papers models.py ran · our draft was wrong MIT (permissive) · 0a330946ecfac712 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22
yangze01/Distilling_the_Knowledge_in_a_Neural_Network_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
train_body joint_main.py unverified no licence file found · pointer only · c3041253233293ca · report
yoshitomo-matsubara/torchdistill community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
compute_accuracy in 81 papers examples/torchvision/image_classification.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · a427a6169de8f607 · report fixture: signature outputs:Tensor/2/float, targets:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-22
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located unverified licence of this copy not recorded · 9b8289076669fe4f · report

Tasks

Knowledge DistillationMixture-of-Experts

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Distillation CIFAR-100 resnet8x4 (T: resnet32x4 S: resnet8x4) Top-1 Accuracy (%) 73.33 #20 of 27 Archive leaderboard report
Knowledge Distillation CIFAR-100 vgg8 (T:vgg13 S:vgg8) Top-1 Accuracy (%) 72.98 #21 of 27 Archive leaderboard report
Knowledge Distillation CIFAR-100 resnet110 (T:resnet110 S:resnet20) Top-1 Accuracy (%) 70.67 #27 of 27 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO(T: ResNet101 S: ResNet50) CRD training setting ✘ #22 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO(T: ResNet101 S: ResNet50) Top-1 accuracy % 77.14 #22 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO(T: ResNet101 S: ResNet50) model size 99M #22 of 52 Archive leaderboard report
Knowledge Distillation ImageNet KD (T: ResNet-34 S:ResNet-18) CRD training setting ✓ #50 of 52 Archive leaderboard report
Knowledge Distillation ImageNet KD (T: ResNet-34 S:ResNet-18) Top-1 accuracy % 70.66 #50 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

Introduced by this paper: Knowledge Distillation

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