SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.05467 · NeurIPS · 2020

Pruning neural networks without any data by iteratively conserving synaptic flow

Daniel Kunin, Surya Ganguli, Daniel Yamins, Hidenori Tanaka

arXiv · PDF · Open in the Atlas

Code that ran

12 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 1 failure of our instrument; 5 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/2006.05467.json · badge: /api/ran/2006.05467.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
iurada/px-ntk-pruning community
Papers with Code archive
7 ran · 4 no recorded run
pvh1602/npb community
Papers with Code archive
2 ran · 0 no recorded run
Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP community
Papers with Code archive
1 ran · 1 no recorded run
apd10/synaptic-flow community
Papers with Code archive
1 ran · 0 no recorded run
yitewang/ntk-sap community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BatchNorm1d Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("7935d0e889ff9eee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

BatchNorm2d Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("bd2e9ef9ef047b34")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Conv2d Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("d526bce01cf543a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Identity1d Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("c09e99a71aca360c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Identity2d Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("f3d19807c24c2f63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Linear Ran
ran on a synthesized input
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("dc24efa85753be6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Pruner Ran
ran on a synthesized input · constructed an object; no result was computed
pvh1602/npb/Pruners/pruners.py
pointer only (licence: NONE) · get_code("e28e1790d31fe600")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pvh1602/npb 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.

SynFlow Ran
ran on a synthesized input · constructed an object; no result was computed
pvh1602/npb/Pruners/pruners.py
pointer only (licence: NONE) · get_code("80271ea817e0be5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pvh1602/npb 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.

SynFlow Ran
ran on a synthesized input · constructed an object; no result was computed
apd10/synaptic-flow/Pruners/pruners.py
pointer only (licence: NONE) · get_code("e7ca315e78c80c60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, apd10/synaptic-flow 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.

SynFlow Ran
ran on a synthesized input · constructed an object; no result was computed
yitewang/ntk-sap/Pruners/pruners.py
code served (permissive licence) · get_code("97a5db95987dac5b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SynFlow: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that works with the SynFlow scorer
class TinyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = TinyModel()

# Create masked_parameters: list of (mask, param) tuples
masked_parameters = []
for name, param in model.named_parameters():
    mask = torch.ones_like(param)
    masked_parameters.append((mask, param))

# Create a simple dataloader: list of (data, label) tuples
# data should have shape (batch_size, *input_dim) where input_dim is [4]
dataloader = [
    (torch.randn(2, 4), torch.randint(0, 2, (2,))),
    (torch.randn(2, 4), torch.randint(0, 2, (2,))),
]

# Define a loss function
def loss_fn(output, target):
    return torch.nn.functional.cross_entropy(output, target)

device = 'cpu'

ARGS = {
    'masked_parameters': masked_parameters,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SynFlow — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SynFlow output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Synflow Ran
ran on a synthesized input · constructed an object; no result was computed
Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP/pruning_method/Synflow.py
pointer only (licence: NONE) · get_code("772bf8519445187f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP 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.

masks Ran
ran; our contract draft was wrong, not the code
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("b4642e3b07dce20e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

Pruner Not yet run
unverified (harvested, no recorded run)
Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP/pruning_method/Synflow.py
pointer only (licence: NONE) · get_code("80f512af69686019")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP 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.

Pruner Not yet run
unverified (harvested, no recorded run)
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("895223082b0c7453")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

SynFlow Not yet run
unverified (harvested, no recorded run)
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("60c6b324705c2d2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

masked_parameters Not yet run
unverified (harvested, no recorded run)
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("3df869cac18fe082")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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.

prunable Not yet run
unverified (harvested, no recorded run)
iurada/px-ntk-pruning/lib/pruners.py
pointer only (licence: NONE) · get_code("3127d6e8725313f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iurada/px-ntk-pruning 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
Linear
brick of this paper's assembly: helper
1 other paper
1 later
2207.03677 (2022-07)
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
Pruner
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
1810.02340 (2018-10)
SNIP: Single-shot Network Pruning based on Connection Sensitivity

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

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable. This theory also elucidates how layer-collapse can be entirely avoided, motivating a novel pruning algorithm Iterative Synaptic Flow Pruning (SynFlow). This algorithm can be interpreted as preserving the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint. Notably, this algorithm makes no reference to the training data and consistently competes with or outperforms existing state-of-the-art pruning algorithms at initialization over a range of models (VGG and ResNet), datasets (CIFAR-10/100 and Tiny ImageNet), and sparsity constraints (up to 99.99 percent). Thus our data-agnostic pruning algorithm challenges the existing paradigm that, at initialization, data must be used to quantify which synapses are important.

For agents

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

get_harvested_code_for_paper("2006.05467")
get_code_for_paper("2006.05467")
have("2006.05467")

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

curl https://syntology.ai/api/ran/2006.05467.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.05467.svg)](https://syntology.ai/paper/2006.05467)

Connect an agent — have() is free.