Papers › LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

18 Jun 2024arXiv:2406.12837archive 2025-07-28

Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song

Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback; the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speed-up while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://github.com/snu-mllab/LayerMerge.

PaperPDFCodeCode Syntology ranMethod as code

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 23 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 11 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: official repository: 23 samples from 1 repository, 17 ran (5 with no instrument failure; 12 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 17 samples that ran have no recorded date.

snu-mllab/layermerge officialmentioned in papermentioned on GitHubpytorchMITSyntology: 23 samples, 17 ran (12 instrument-failed) · 6 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.

Code Syntology ran Syntology

23 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
11ran · our draft was wrong
1ran; the contract check could not run
2ran
6unverified

Licence: 2 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 snu-mllab/layermerge. “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.

snu-mllab/layermerge official repository 23 samples, 17 ran (12 instrument-failed) · 6 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
layer_merge/trainer.py ran MIT (permissive) · 9230e14bc7473f01 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-24
adjust_with_bn layer_merge/models/merge_op.py ran · our draft was wrong MIT (permissive) · 0aef496f982bd284 · report fixture: signature conv_weight:Tensor/2/float, bias:Tensor/1/float, bn:callable/0/? · returned tuple · level recorded 2026-09-22
conv1x1 in 691 papers HALP/models/resnet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers HALP/models/resnet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv_with_new layer_merge/models/merge_op.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 7e877f94c66d280c · report fixture: signature old_conv:Tensor/4/float, old_bias:Tensor/1/float, new_conv:Tensor/4/float, stride:int/0/int, padding:int/0/int · returned tuple · level recorded 2026-09-22
dict2namespace in 31 papers Diff-Pruning/exp_code/finetune.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bd1f17e427bf51a5 · report fixture: signature config:dict/0/? · returned Namespace · level recorded, date not recorded
get_beta_schedule in 66 papers layer_merge/ddpm_trainer.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · ca0cea1ca1eeec89 · report fixture: signature beta_schedule:str/0/str, beta_start:float/0/float, beta_end:float/0/float, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
merge_or_new layer_merge/models/merge_op.py ran · our draft was wrong MIT (permissive) · b698fd9df5f648a6 · report fixture: signature m_layers:list/1/tuple, pos:int/0/int, weights:tuple/1/int, lyrs:tuple/1/callable, merged:bool/0/bool, cparam:tuple/1/str, pop_k:int/0/int · returned tuple · level recorded 2026-09-22
natural_key in 10 papers layer_merge/aggregate_imp.py ran · our draft was wrong fingerprinted MIT (permissive) · c5f7f81b1ed8389e · report fixture: signature string_:str/0/str · returned list · level recorded 2026-09-24
noise_estimation_loss in 19 papers layer_merge/ddpm_trainer.py ran MIT (permissive) · 36a45cceb1209d2f · report fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
unroll_bias_params Efficient-CNN-Depth-Compression/models/model_op.py ran · honoured contract MIT (permissive) · da634e83bc73dbc2 · report fixture: signature bias:callable/0/? · returned Tensor · level recorded 2026-09-24
unroll_bn_params layer_merge/models/merge_op.py ran · honoured contract MIT (permissive) · afce56cbc2fd5872 · report fixture: signature bn:callable/0/? · returned tuple · level recorded 2026-09-22
unroll_conv_params layer_merge/models/merge_op.py ran · our draft was wrong MIT (permissive) · 766adfb76c25bc6b · report fixture: signature conv:callable/0/?, dw:bool/0/bool · returned tuple · level recorded 2026-09-22
unroll_conv_params Efficient-CNN-Depth-Compression/models/model_op.py ran · our draft was wrong MIT (permissive) · b05267fb07337f46 · report fixture: signature conv:callable/0/?, dw:bool/0/bool · returned tuple · level recorded 2026-09-24
unroll_merged layer_merge/measure.py ran · our draft was wrong MIT (permissive) · 85ac542b88d8f697 · report fixture: signature module:callable/0/? · returned Sequential · level recorded 2026-09-24
unroll_merged_vgg layer_merge/measure.py ran · our draft was wrong MIT (permissive) · 1084591b0a6b8b62 · report fixture: signature module:callable/0/? · returned Sequential · level recorded 2026-09-24
update_m_weights layer_merge/models/merge_op.py ran · our draft was wrong MIT (permissive) · d55563e057db09b2 · report fixture: signature isize:int/0/int, m_cw:Tensor/4/float, m_p:int/0/int, m_b:Tensor/1/float, conv:callable/0/?, bn:callable/0/?, merged:bool/0/bool · returned tuple · level recorded 2026-09-22
ResNet18 in 174 papers HALP/models/resnet.py unverified MIT (permissive) · 7ca664ad5eb99003 · report
calculate_activation_statistics in 75 papers Diff-Pruning/exp_code/fid_score.py unverified MIT (permissive) · 2e647db33e6bd721 · report
calculate_frechet_distance in 119 papers Diff-Pruning/exp_code/fid_score.py unverified MIT (permissive) · 0def50a351111624 · report
get_activations in 100 papers Diff-Pruning/exp_code/fid_score.py unverified MIT (permissive) · 1af4059005f8a78d · report
get_time in 20 papers layer_merge/measure.py unverified MIT (permissive) · 53138d8dfe29a2a5 · report
parse_args_and_config Diff-Pruning/exp_code/finetune.py unverified MIT (permissive) · ed8e294ff23d95ea · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LayerMerge (graph method: LayerMerge). 6 bricks; individually on a fixture: 6 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; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. merge_or_new entry · level 1 · ran · our draft was wrong · b698fd9df5f648a6
  2. update_m_weights helper · level 1 · ran · our draft was wrong · d55563e057db09b2
  3. adjust_with_bn helper · level 1 · ran · our draft was wrong · 0aef496f982bd284
  4. conv_with_new helper · level 1 · ran; the contract check could not run (RAISES) · 7e877f94c66d280c
  5. unroll_conv_params helper · level 1 · ran · our draft was wrong · 766adfb76c25bc6b
  6. unroll_bn_params helper · level 1 · ran · honoured contract · afce56cbc2fd5872

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.12837") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionPruning

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