Papers › Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

17 Sep 2019arXiv:1909.08097archive 2025-07-28

Umar Asif, Jianbin Tang, Stefan Harrer

Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements. In this paper, we present a framework for learning compact CNN models with improved classification performance and model generalization. For this, we propose a CNN architecture of a compact student model with parallel branches which are trained using ground truth labels and information from high capacity teacher networks in an ensemble learning fashion. Our framework provides two main benefits: i) Distilling knowledge from different teachers into the student network promotes heterogeneity in feature learning at different branches of the student network and enables the network to learn diverse solutions to the target problem. ii) Coupling the branches of the student network through ensembling encourages collaboration and improves the quality of the final predictions by reducing variance in the network outputs. Experiments on the well established CIFAR-10 and CIFAR-100 datasets show that our Ensemble Knowledge Distillation (EKD) improves classification accuracy and model generalization especially in situations with limited training data. Experiments also show that our EKD based compact networks outperform in terms of mean accuracy on the test datasets compared to state-of-the-art knowledge distillation based methods.

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 6 code samples harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 6 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). 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 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

softsys4ai/neural-distiller mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional... (arXiv:1909.08174; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Adlik/model_optimizer pytorchApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified 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

6 samples harvested: 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. “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.

5ran
1unverified

Licence: 0 of the 6 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 Adlik/model_optimizer. “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.

Adlik/model_optimizer community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/model_optimizer/core/utils.py ran Apache-2.0 (permissive) · 5cb9054e3353acdb · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-24
check_input_data src/model_optimizer/quantizer/deploy_fx_with_backend.py ran Apache-2.0 (permissive) · 3b1c6af3a7240f56 · report fixture: signature input_data:list/1/int · returned list · level recorded 2026-09-24
fake_quantize_per_channel_affine src/model_optimizer/quantizer/fake_quantize.py ran Apache-2.0 (permissive) · 184af36e7222c153 · report fixture: signature g:MockGraph/0/?, x:Tensor/4/float, scale:Tensor/1/float, zero_point:Tensor/1/int, ch_axis:int/0/int, quant_min:int/0/int, quant_max:int/0/int · returned str · level recorded 2026-09-24
fake_quantize_per_tensor_affine src/model_optimizer/quantizer/fake_quantize.py ran Apache-2.0 (permissive) · cdfa1049b88fc86a · report fixture: signature g:FakeGraph/0/?, x:Tensor/2/float, scale:Tensor/0/float, zero_point:Tensor/0/int, quant_min:Tensor/0/int, quant_max:Tensor/0/int · returned str · level recorded 2026-09-24
register_parser src/model_optimizer/pruners/structure_pruning.py ran Apache-2.0 (permissive) · ca2d9e1876635ca0 · report fixture: signature parser_dict:dict/0/?, name:str/0/str, force:bool/0/bool · returned function · level recorded 2026-09-24
fused_moving_avg_obs_fake_quant src/model_optimizer/quantizer/fake_quantize.py unverified Apache-2.0 (permissive) · a8e0390827e00583 · report

Tasks

Ensemble LearningGeneral ClassificationKnowledge Distillation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Distillation ImageNet ADLIK-MO-P25(T:SeNet154, ResNet152b S:ResNet-50-prune25%) CRD training setting ✘ #17 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P25(T:SeNet154, ResNet152b S:ResNet-50-prune25%) Top-1 accuracy % 78.79 #17 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P25(T:SeNet154, ResNet152b S:ResNet-50-prune25%) model size 56.9M #17 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P375(T:SeNet154, ResNet152b S:ResNet-50-prune37.5) CRD training setting ✘ #18 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P375(T:SeNet154, ResNet152b S:ResNet-50-prune37.5) Top-1 accuracy % 78.07 #18 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P375(T:SeNet154, ResNet152b S:ResNet-50-prune37.5) model size 40.5M #18 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P50(T:SeNet154, ResNet152b S:ResNet-50-half) CRD training setting ✘ #24 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P50(T:SeNet154, ResNet152b S:ResNet-50-half) Top-1 accuracy % 76.376 #24 of 52 Archive leaderboard report
Knowledge Distillation ImageNet ADLIK-MO-P50(T:SeNet154, ResNet152b S:ResNet-50-half) model size 27M #24 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