SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.01633 · 2020

Structural Deep Clustering Network

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.01633.json · badge: /api/ran/2002.01633.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
bdy9527/SDCN canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
461054993/SDCN community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
load_graph Ran
ran on a synthesized input
461054993/SDCN/utils.py
code served (permissive licence) · get_code("25fe78ad026472c5")
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 Tensor. 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 numpy as np
import scipy.sparse as sp
import torch
import tempfile
import os

torch.manual_seed(0)

# Create temporary directory and mock data files
tmpdir = tempfile.mkdtemp()
data_dir = os.path.join(tmpdir, 'data')
graph_dir = os.path.join(tmpdir, 'graph')
os.makedirs(data_dir, exist_ok=True)
os.makedirs(graph_dir, exist_ok=True)

# Create mock data file
dataset_name = 'test_dataset'
data_file = os.path.join(data_dir, f'{dataset_name}.txt')
data = np.random.rand(5, 3).astype(np.float32)
np.savetxt(data_file, data)

# Create mock graph file (edges)
graph_file = os.path.join(graph_dir, f'{dataset_name}_graph.txt')
edges = np.array([[0, 1], [1, 2], [2, 3], [3, 4], [4, 0]], dtype=np.int32)
np.savetxt(graph_file, edges, fmt='%d')

# Change to temporary directory so relative paths work
original_dir = os.getcwd()
os.chdir(tmpdir)

ARGS = {
    'dataset': 'test_dataset',
    'k': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (5, 5) — shape (5, 5) as a later run recorded it
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
normalize Ran
ran, violated the contract we drafted
461054993/SDCN/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from songw-sw/x-fnc, is pointer only (licence: NONE) · get_code("aa9c29936dee40a7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from songw-sw/x-fnc, 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.

sparse_mx_to_torch_sparse_tensor Ran
ran; our contract draft was wrong, not the code
461054993/SDCN/utils.py
code served (permissive licence) · get_code("c97b99c4e8201a97")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor. 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 numpy as np
import torch
from scipy.sparse import csr_matrix

torch.manual_seed(0)

# Create a small sparse matrix using scipy
# Make it 3x4 to have distinct dimensions
row = np.array([0, 0, 1, 2, 2])
col = np.array([0, 2, 1, 0, 3])
data = np.array([1.5, 2.3, 3.7, 4.2, 5.1])
sparse_mx = csr_matrix((data, (row, col)), shape=(3, 4))

ARGS = {
    'sparse_mx': sparse_mx
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (3, 4) — shape (3, 4) as a later run recorded it
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
target_distribution Ran
ran, honoured the contract we drafted
bdy9527/SDCN/sdcn.py
code served (permissive licence) · get_code("c8b8a6955c6ca85d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch.nn as nn

torch.manual_seed(0)

# The function takes a tensor q and performs operations:
# - q ** 2: element-wise squaring
# - q.sum(0): sum along dimension 0
# - weight.t(): transpose
# - weight.sum(1): sum along dimension 1
# The parameter q should be a 2D tensor (samples x clusters)

q = torch.rand(2, 4)  # batch_size=2, num_clusters=4

ARGS = {
    "q": q
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
sparse_mx_to_torch_sparse_tensor 32 other papers
2 dated earlier, 30 later · 4 only as an assembly brick
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1902.07153 (2019-02)
Simplifying Graph Convolutional Networks
2004.01899 (2020-04)
A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
and 29 more not named here
normalize 24 other papers
5 dated earlier, 19 later
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
1803.03735 (2018-03)
Attention-based Graph Neural Network for Semi-supervised Learning
1805.09112 (2018-05)
Hyperbolic Neural Networks
and 21 more not named here
target_distribution 8 other papers
1 dated earlier, 7 later
1906.06532 (2019-06)
Attributed Graph Clustering: A Deep Attentional Embedding Approach
2009.11407 (2020-09)
Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19
2211.12875 (2022-11)
A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource
and 5 more not named here

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful representation ability of deep learning, e.g., autoencoder, suggesting that learning an effective representation for clustering is a crucial requirement. The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning. Motivated by the great success of Graph Convolutional Network (GCN) in encoding the graph structure, we propose a Structural Deep Clustering Network (SDCN) to integrate the structural information into deep clustering. Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model. In this way, the multiple structures of data, from low-order to high-order, are naturally combined with the multiple representations learned by autoencoder. Furthermore, we theoretically analyze the delivery operator, i.e., with the delivery operator, GCN improves the autoencoder-specific representation as a high-order graph regularization constraint and autoencoder helps alleviate the over-smoothing problem in GCN. Through comprehensive experiments, we demonstrate that our propose model can consistently perform better over the state-of-the-art techniques.

For agents

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

get_harvested_code_for_paper("2002.01633")
get_code_for_paper("2002.01633")
have("2002.01633")

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

curl https://syntology.ai/api/ran/2002.01633.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.01633.svg)](https://syntology.ai/paper/2002.01633)

Connect an agent — have() is free.