SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.14729 · CVPR · 2024

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch

Shangqian Gao, Heng Huang, Xiaoqian Wang, Zeyu Zhang, Runxue Bao, Zhenzhen Li, Xidong Wu, Yanfu Zhang

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 8 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.14729.json · badge: /api/ran/2403.14729.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
xidongwu/autotrainonce canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
xidongwu/AutoTrainOnce community
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
HyperStructure Ran
ran on a synthesized input · constructed an object; no result was computed
xidongwu/AutoTrainOnce/imgnet_models/hypernet.py
pointer only (licence: NONE) · get_code("f890ddff61fb91f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/AutoTrainOnce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TrainVal_split Ran
ran on a synthesized input
xidongwu/autotrainonce/utils.py
pointer only (licence: NONE) · get_code("c4592ff12f5fc0ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

binary_loss Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/utils.py
pointer only (licence: NONE) · get_code("3e4246d9e07a4a5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv1x1 Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/imgnet_models/resnet_gate.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv3x3 Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/imgnet_models/resnet_gate.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/imgnet_models/mobilenetv2_custom.py
pointer only (licence: NONE); the stored copy get_code serves, from zhoudaquan/rethinking_bottleneck_design, is pointer only (licence: NOASSERTION) · get_code("a0131fb70c267a9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_3x3_bn Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/imgnet_models/mobilenetv2_custom.py
pointer only (licence: NONE); the stored copy get_code serves, from zhoudaquan/rethinking_bottleneck_design, is pointer only (licence: NOASSERTION) · get_code("408e747e0425a594")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

display_structure_hyper Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/utils.py
pointer only (licence: NONE) · get_code("f531ac13d278e937")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gumbel_softmax_sample Ran
ran, honoured the contract we drafted
xidongwu/AutoTrainOnce/imgnet_models/hypernet.py
pointer only (licence: NONE) · get_code("82162a6032091037")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/AutoTrainOnce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hard_concrete Ran
ran, honoured the contract we drafted
xidongwu/AutoTrainOnce/imgnet_models/hypernet.py
pointer only (licence: NONE) · get_code("ea3641e05d15494f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/AutoTrainOnce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_gumbel Ran
ran; our contract draft was wrong, not the code
xidongwu/AutoTrainOnce/imgnet_models/hypernet.py
pointer only (licence: NONE) · get_code("2908a8bdfec77e29")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/AutoTrainOnce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tanh_gradient Ran
ran; our contract draft was wrong, not the code
xidongwu/autotrainonce/imgnet_models/gate_function.py
pointer only (licence: NONE) · get_code("f6b2928cdbf646f1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prob_round_torch Not yet run
unverified (harvested, no recorded run)
xidongwu/autotrainonce/imgnet_models/gate_function.py
pointer only (licence: NONE) · get_code("d1c3d5733eccf3d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
xidongwu/autotrainonce/imgnet_models/resnet_gate.py
pointer only (licence: NONE) · get_code("ffa69fc58b9aa203")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xidongwu/autotrainonce when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 6 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
330 dated earlier, 13 the same month, 77 later, 10 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
226 dated earlier, 11 the same month, 64 later, 10 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
64 dated earlier, 3 the same month, 24 later, 3 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
conv_1x1_bn 31 other papers
28 dated earlier, 3 later · 2 only as an assembly brick
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 28 more not named here
conv_3x3_bn 12 other papers
10 dated earlier, 2 later
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1904.07399 (2019-04)
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
1911.08114 (2019-11)
Neural Network Pruning with Residual-Connections and Limited-Data
and 9 more not named here
sample_gumbel
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable · 1 only as an assembly brick
1910.09387 (2019-10)
Clotho: An Audio Captioning Dataset
aaai_29990 (2024 (year only))
GOALNET: Interleaving Neural Goal Predicate Inference with Classical Planning for Generalization in Robot Instruction Following
2410.11988 (2024-10)
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging. To address the limitation, the Only-Train-Once (OTO) and OTOv2 are proposed to eliminate the need for additional fine-tuning steps by directly training and compressing a general DNN from scratch. Nevertheless, the static design of optimizers (in OTO) can lead to convergence issues of local optima. In this paper, we proposed the Auto-Train-Once (ATO), an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. During the model training phase, our approach not only trains the target model but also leverages a controller network as an architecture generator to guide the learning of target model weights. Furthermore, we developed a novel stochastic gradient algorithm that enhances the coordination between model training and controller network training, thereby improving pruning performance. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves stateof-the-art performance across various model architectures (including ResNet18, ResNet34, ResNet50, ResNet56, and MobileNetv2) on standard benchmark datasets (CIFAR-10, CIFAR-100, and ImageNet). The code is available at https://github.com/xidongwu/AutoTrainOnce.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.14729")
get_code_for_paper("2403.14729")
have("2403.14729")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.14729.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.14729.svg)](https://syntology.ai/paper/2403.14729)

Connect an agent — have() is free.