Papers › Knapsack Pruning with Inner Distillation

Knapsack Pruning with Inner Distillation

19 Feb 2020arXiv:2002.08258archive 2025-07-28

Yonathan Aflalo, Asaf Noy, Ming Lin, Itamar Friedman, Lihi Zelnik

Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from ℓ₁-norm sparsification to Neural Architecture Search (NAS). In this work, we propose a novel pruning method that optimizes the final accuracy of the pruned network and distills knowledge from the over-parameterized parent network's inner layers. To enable this approach, we formulate the network pruning as a Knapsack Problem which optimizes the trade-off between the importance of neurons and their associated computational cost. Then we prune the network channels while maintaining the high-level structure of the network. The pruned network is fine-tuned under the supervision of the parent network using its inner network knowledge, a technique we refer to as the Inner Knowledge Distillation. Our method leads to state-of-the-art pruning results on ImageNet, CIFAR-10 and CIFAR-100 using ResNet backbones. To prune complex network structures such as convolutions with skip-links and depth-wise convolutions, we propose a block grouping approach to cope with these structures. Through this we produce compact architectures with the same FLOPs as EfficientNet-B0 and MobileNetV3 but with higher accuracy, by 1% and 0.3% respectively on ImageNet, and faster runtime on GPU.

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="2002.08258")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yoniaflalo/knapsack_pruning officialmentioned on GitHubpytorch 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

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 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

Licence: 0 of the 3 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 yoniaflalo/knapsack_pruning. “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.

extract_conv_layers yoniaflalo/knapsack_pruning/external/utils_pruning.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 3f24b14f913cebed · report
extract_layer yoniaflalo/knapsack_pruning/external/utils_pruning.py official repository ran · our draft was wrong Apache-2.0 (permissive) · c8a06e6ec83e9e27 · report
extract_layers yoniaflalo/knapsack_pruning/external/utils_pruning.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 9e0ce49dce5bd330 · report

Tasks

Knowledge DistillationNetwork PruningNeural Architecture Search

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Network Pruning ImageNet ResNet50 2.5 GFLOPS Accuracy 78.0 #3 of 16 Archive leaderboard report
Network Pruning ImageNet ResNet50 2.5 GFLOPS GFLOPs 2.5 #3 of 16 Archive leaderboard report
Network Pruning ImageNet ResNet50 2.0 GFLOPS Accuracy 77.70 #5 of 16 Archive leaderboard report
Network Pruning ImageNet ResNet50 2.0 GFLOPS GFLOPs 2 #5 of 16 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsGlobal Average PoolingKaiming InitializationKnowledge DistillationMax PoolingPruningReLUResidual BlockResidual Connection

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