SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14085 · 2020

Topological Insights into Sparse Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 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; 2 failures of our instrument; 1 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/2006.14085.json · badge: /api/ran/2006.14085.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
adubowski/set-mlp-keras community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
createSparseWeights Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from dcmocanu/sparse-evolutionary-artificial-neural-networks
pointer only · get_code("d1dd6b1240c82834")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

createWeightsMask Ran
ran; our contract draft was wrong, not the code
adubowski/set-mlp-keras/SET-MLP-Keras-Weights-Mask/fixprob_mlp_keras_cifar10.py
pointer only (licence: MIT); the stored copy get_code serves, from joostPieterse/CosineSET, is pointer only (licence: NONE) · get_code("1cb2d51570c25ff3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from joostPieterse/CosineSET, and GitHub detected no licence in that repository 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.

find_first_pos Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from joostPieterse/CosineSET
pointer only; the stored copy get_code serves, from joostPieterse/CosineSET, is pointer only (licence: NONE) · get_code("09540a28779b66ce")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

find_last_pos Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from joostPieterse/CosineSET
pointer only; the stored copy get_code serves, from joostPieterse/CosineSET, is pointer only (licence: NONE) · get_code("6c42c3044030b535")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

rolling_window Ran
ran on a synthesized input
adubowski/set-mlp-keras/SET-MLP-Keras-Weights-Mask/plot_overfitting_per_sparsity.py
pointer only (licence: MIT); the stored copy get_code serves, from knowledgetechnologyuhh/goal_conditioned_RL_baselines, is pointer only (licence: MIT) · get_code("895ca4b776fb6d6d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from knowledgetechnologyuhh/goal_conditioned_RL_baselines, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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.

sreluPlot Ran
ran on a synthesized input
adubowski/set-mlp-keras/SET-MLP-Keras-Weights-Mask/plot_functions.py
code served (permissive licence) · get_code("e84c822cd2101b70")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

torch.manual_seed(0)

# sreluPlot takes a single numeric argument x
# The function performs conditional logic on x comparing it to scalar thresholds (0.8, -0.8)
# and returns a scalar value based on which branch is taken

# We'll test with a simple scalar value
x = 0.5

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
swish Not yet run
unverified (harvested, no recorded run)
adubowski/set-mlp-keras/SET-MLP-Keras-Weights-Mask/dense_mlp_keras_cifar10.py
code served (permissive licence) · get_code("6f8448154976771e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 2 later) and 2 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
rolling_window 12 other papers
8 dated earlier, 1 the same month, 3 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 9 more not named here
find_first_pos 4 other papers
3 dated earlier, 1 later
1707.04780 (2017-07)
Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
1901.09181 (2019-01)
Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
1903.07138 (2019-03)
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
and 1 more not named here
find_last_pos 3 other papers
3 dated earlier
1707.04780 (2017-07)
Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
1901.09181 (2019-01)
Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
1903.07138 (2019-03)
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
createSparseWeights 2 other papers
2 dated earlier
1707.04780 (2017-07)
Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
1901.09181 (2019-01)
Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
createWeightsMask 2 other papers
2 dated earlier
1901.09181 (2019-01)
Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
1903.07138 (2019-03)
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks

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

Sparse neural networks are effective approaches to reduce the resource requirements for the deployment of deep neural networks. Recently, the concept of adaptive sparse connectivity, has emerged to allow training sparse neural networks from scratch by optimizing the sparse structure during training. However, comparing different sparse topologies and determining how sparse topologies evolve during training, especially for the situation in which the sparse structure optimization is involved, remain as challenging open questions. This comparison becomes increasingly complex as the number of possible topological comparisons increases exponentially with the size of networks. In this work, we introduce an approach to understand and compare sparse neural network topologies from the perspective of graph theory. We first propose Neural Network Sparse Topology Distance (NNSTD) to measure the distance between different sparse neural networks. Further, we demonstrate that sparse neural networks can outperform over-parameterized models in terms of performance, even without any further structure optimization. To the end, we also show that adaptive sparse connectivity can always unveil a plenitude of sparse sub-networks with very different topologies which outperform the dense model, by quantifying and comparing their topological evolutionary processes. The latter findings complement the Lottery Ticket Hypothesis by showing that there is a much more efficient and robust way to find "winning tickets". Altogether, our results start enabling a better theoretical understanding of sparse neural networks, and demonstrate the utility of using graph theory to analyze them.

For agents

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

get_harvested_code_for_paper("2006.14085")
get_code_for_paper("2006.14085")
have("2006.14085")

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

curl https://syntology.ai/api/ran/2006.14085.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.14085.svg)](https://syntology.ai/paper/2006.14085)

Connect an agent — have() is free.