SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.06532 · 2019

Attributed Graph Clustering: A Deep Attentional Embedding Approach

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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, 0 violated it and 5 have no contract verdict; 1 failure 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/1906.06532.json · badge: /api/ran/1906.06532.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
Tiger101010/DAEGC community (classifier label)
classifier basis: plan_row
3 ran · 1 no recorded run
GraphEoM/GSCAN community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
covert_to_graph Ran
ran on a synthesized input
GraphEoM/GSCAN/gscan/gnn.py
code served (permissive licence) · get_code("be892fda44df7c50")
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 tuple. 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 pandas as pd

# Create a small dataframe for nodes with node names, features, and labels
nodes_df = pd.DataFrame({
    'node_id': ['A', 'B', 'C', 'D'],
    'feature_1': [1.0, 2.0, 3.0, 4.0],
    'feature_2': [5.0, 6.0, 7.0, 8.0],
    'feature_3': [9.0, 10.0, 11.0, 12.0],
    'label': [0, 1, 0, 1]
})

# Create a small dataframe for edges (connections between nodes)
edges_df = pd.DataFrame({
    'source': ['A', 'B', 'C'],
    'target': ['B', 'C', 'D']
})

ARGS = {
    'nodes': nodes_df,
    'edges': edges_df,
    'name': 'node_id',
    'features': ['feature_1', 'feature_2', 'feature_3'],
    'label': 'label'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
data_preprocessing Ran
ran on a synthesized input
Tiger101010/DAEGC/DAEGC/utils.py
code served (permissive licence) · get_code("95dd16f7e992d4ef")
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 MockDataset. 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
from torch_geometric.data import Data

torch.manual_seed(0)

# Create a minimal dataset object with required attributes
class MockDataset:
    def __init__(self):
        # Create a small graph with 3 nodes and 4 edges
        self.x = torch.randn(3, 4)  # 3 nodes, 4 features
        # edge_index: 2 x num_edges
        self.edge_index = torch.tensor([
            [0, 1, 1, 2],
            [1, 0, 2, 1]
        ], dtype=torch.long)
        self.adj = None
        self.adj_label = None

dataset = MockDataset()

ARGS = {
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sklearn, torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockDataset — a MockDataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockDataset 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
dot_product_decode Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from DaehanKim/vgae_pytorch
pointer only · get_code("ae488d391f6d24c2")
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.

evl Ran
ran on a synthesized input
GraphEoM/GSCAN/gscan/evaluation.py
code served (permissive licence) · get_code("3105a1506684aeb3")
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 dict. 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

# Create small ground truth labels and predicted cluster labels
# Using distinct sizes to avoid ambiguity
np.random.seed(0)

# Ground truth labels: 5 samples with 3 true clusters (0, 1, 2)
y_tru = np.array([0, 0, 1, 1, 2])

# Predicted cluster labels: 5 samples assigned to clusters (0, 1, 0, 2, 1)
y_prd = np.array([0, 1, 0, 2, 1])

ARGS = {
    'y_tru': y_tru,
    'y_prd': y_prd
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
f1 Ran
ran on a synthesized input
GraphEoM/GSCAN/gscan/evaluation.py
code served (permissive licence) · get_code("681f6a5cb5d508f9")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Construct test data for the f1 function
# y_tru: ground truth labels (should be integers from 0 to dim1-1)
# y_prd: predicted/cluster labels (should be integers from 0 to dim2-1)

# Create small, distinct ground truth labels (4 samples, 3 unique classes)
y_tru = np.array([0, 1, 2, 0], dtype=int)

# Create small, distinct predicted labels (4 samples, 3 unique classes)
y_prd = np.array([0, 1, 1, 2], dtype=int)

ARGS = {
    "y_tru": y_tru,
    "y_prd": y_prd,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
get_M Ran
ran on a synthesized input
Tiger101010/DAEGC/DAEGC/utils.py
code served (permissive licence) · get_code("8b4c02cc305198d9")
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 (4, 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 numpy as np
from scipy import sparse

torch.manual_seed(0)

# Create a small adjacency matrix as a torch tensor
# Using a 4x4 sparse-like adjacency matrix for a small graph
adj_numpy = np.array([
    [0.0, 0.5, 0.3, 0.2],
    [0.5, 0.0, 0.2, 0.3],
    [0.3, 0.2, 0.0, 0.5],
    [0.2, 0.3, 0.5, 0.0]
], dtype=np.float32)

adj = torch.Tensor(adj_numpy)

ARGS = {
    "adj": adj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn, 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 (4, 4) — shape (4, 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
target_distribution Ran
ran, honoured the contract we drafted
Tiger101010/DAEGC/DAEGC/daegc.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
get_dataset Not yet run
unverified (harvested, no recorded run)
Tiger101010/DAEGC/DAEGC/utils.py
code served (permissive licence) · get_code("849248c0666eb6f8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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, 2 later) and 6 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
target_distribution 8 other papers
8 later
2002.01633 (2020-02)
Structural Deep Clustering Network
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
dot_product_decode 3 other papers
1 dated earlier, 2 later
1611.07308 (2016-11)
Variational Graph Auto-Encoders
2106.00967 (2021-06)
Multiresolution Equivariant Graph Variational Autoencoder
2407.04999 (2024-07)
Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs

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

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.

For agents

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

get_harvested_code_for_paper("1906.06532")
get_code_for_paper("1906.06532")
have("1906.06532")

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

curl https://syntology.ai/api/ran/1906.06532.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.06532.svg)](https://syntology.ai/paper/1906.06532)

Connect an agent — have() is free.