SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.06755 · 2020

Unifying Graph Convolutional Neural Networks and Label Propagation

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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 7 have no contract verdict; 0 failures of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2002.06755.json · badge: /api/ran/2002.06755.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
achalagarwal/gcn-lpa community (classifier label)
classifier basis not recorded on the link
8 ran · 2 no recorded run
hwwang55/GCN-LPA community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
sigmoid Ran
ran, violated the contract we drafted
achalagarwal/gcn-lpa/src/karate_club.py
code served (permissive licence) · get_code("b8e95809ca2c17c9")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T02:39:00Z). 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 numpy as np

# The sigmoid function takes a single parameter 'x' which should be a numeric value or array
# Looking at the function body, it performs: 1 / (1 + np.exp(-x))
# This works with scalars, lists, or numpy arrays

# Create a small numpy array to pass as input
x_input = np.array([0.0, 1.0, -1.0, 2.0])

ARGS = {
    "x": x_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
dot Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/layers.py
code served (permissive licence) · get_code("29e29535d9eada4d")
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 EagerTensor, ndim 2, dtype family float, shape (2, 2) 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 tensorflow as tf
import numpy as np

# Create a dense matrix for y (always used in matmul)
y_dense = tf.constant([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0], [7.0, 8.0]], dtype=tf.float32)

# Create a dense matrix x for the non-sparse case
x_dense = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

# Create a sparse matrix x for the sparse case
# Build as COO format: shape (2, 4), needs to be compatible with y shape (4, 2)
indices = [[0, 0], [0, 2], [1, 1], [1, 3]]
values = [1.0, 2.0, 3.0, 4.0]
x_sparse = tf.SparseTensor(indices=indices, values=values, dense_shape=[2, 4])

# Test with sparse=True
ARGS = {
    "x": x_sparse,
    "y": y_dense,
    "sparse": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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
dot Ran
ran on a synthesized input
hwwang55/GCN-LPA/src/layers.py
code served (permissive licence) · get_code("585faba8d93889b9")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create a small dense tensor (2x3)
x_dense = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype=tf.float32)

# Create a small dense tensor (3x4)
y_dense = tf.constant([[1.0, 2.0, 3.0, 4.0], 
                       [5.0, 6.0, 7.0, 8.0],
                       [9.0, 10.0, 11.0, 12.0]], dtype=tf.float32)

# Create sparse version of x (2x3)
indices_x = tf.constant([[0, 0], [1, 2]], dtype=tf.int64)
values_x = tf.constant([1.0, 6.0], dtype=tf.float32)
x_sparse = tf.SparseTensor(indices=indices_x, values=values_x, dense_shape=[2, 3])

# Create sparse version of y (3x4)
indices_y = tf.constant([[0, 0], [1, 1], [2, 3]], dtype=tf.int64)
values_y = tf.constant([1.0, 6.0, 12.0], dtype=tf.float32)
y_sparse = tf.SparseTensor(indices=indices_y, values=values_y, dense_shape=[3, 4])

ARGS = {
    "x": x_dense,
    "y": y_dense,
    "sparse": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
glorot Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/inits.py
code served (permissive licence) · get_code("0ff0dc0369c94cbe")
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 ResourceVariable, ndim 2, dtype family float, shape (4, 3) 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
np.random.seed(0)
tf.random.set_seed(0)

# The function takes a shape (tuple of ints) and an optional name string
# shape: determines the dimensions of the uniform random variable
# name: optional name for the tf.Variable

ARGS = {
    "shape": (4, 3),
    "name": "glorot_weights"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResourceVariable, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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
normalize_features Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/data_loader.py
code served (permissive licence) · get_code("33746814a1d4ff92")
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 csr_matrix. 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

# Create a small sparse matrix for testing
# The function expects a sparse matrix with shape (n_samples, n_features)
# Using distinct dimensions: 4 rows, 3 columns
rows = np.array([0, 0, 1, 2, 2, 3])
cols = np.array([0, 1, 1, 0, 2, 2])
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
features = sp.csr_matrix((data, (rows, cols)), shape=(4, 3))

ARGS = {
    "features": features
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
parse_index_file Ran
ran, honoured the contract we drafted
achalagarwal/gcn-lpa/src/data_loader.py
code served (permissive licence) · get_code("5c3fa9402a9405bc")
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) and returned list, ndim 1, dtype family int; 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 tempfile
import os

# Create a temporary file with index data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0\n")
temp_file.write("1\n")
temp_file.write("5\n")
temp_file.write("3\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
sparse_to_tuple Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/data_loader.py
code served (permissive licence) · get_code("13c5950f6e3ab34b")
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 scipy.sparse as sp

# Create a small sparse matrix in COO format
rows = np.array([0, 1, 2, 2])
cols = np.array([0, 1, 0, 2])
data = np.array([1.0, 2.0, 3.0, 4.0])
sparse_matrix = sp.coo_matrix((data, (rows, cols)), shape=(3, 4))

ARGS = {
    "sparse_matrix": sparse_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
uniform Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/inits.py
code served (permissive licence) · get_code("5215c72b1d4d573c")
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 ResourceVariable, 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 tensorflow as tf

# The function takes three parameters: shape, scale, and name
# - shape: tuple/list defining the shape of the random uniform tensor
# - scale: float controlling the range [-scale, scale]
# - name: optional string name for the variable

ARGS = {
    "shape": (2, 4),
    "scale": 0.05,
    "name": "test_uniform_var"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResourceVariable, 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
zeros Ran
ran on a synthesized input
achalagarwal/gcn-lpa/src/inits.py
code served (permissive licence) · get_code("595ca46a0fcb65fa")
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 ResourceVariable, 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 tensorflow as tf

def zeros(shape, name=None):
    initial = tf.zeros(shape, dtype=tf.float64)
    return tf.Variable(initial, name=name)

# Setup code
shape_value = (2, 4)
name_value = "test_variable"

ARGS = {
    "shape": shape_value,
    "name": name_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResourceVariable, 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_layer_uid Not yet run
unverified (harvested, no recorded run)
achalagarwal/gcn-lpa/src/layers.py
code served (permissive licence) · get_code("2d68c4193e0780cb")
How it ran

no invocation recorded.

glorot Not yet run
unverified (harvested, no recorded run)
hwwang55/GCN-LPA/src/inits.py
code served (permissive licence) · get_code("8efce639c727cd2d")
How it ran

no invocation recorded.

sparse_dropout Not yet run
unverified (harvested, no recorded run)
achalagarwal/gcn-lpa/src/layers.py
code served (permissive licence) · get_code("cd61377ca3953238")
How it ran

no invocation recorded.

sparse_dropout Not yet run
unverified (harvested, no recorded run)
hwwang55/GCN-LPA/src/layers.py
code served (permissive licence) · get_code("ce452a33739aaed9")
How it ran

no invocation recorded.

uniform Not yet run
unverified (harvested, no recorded run)
hwwang55/GCN-LPA/src/inits.py
code served (permissive licence) · get_code("f433ebe52ac58c73")
How it ran

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 11 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
parse_index_file 53 other papers
21 dated earlier, 2 the same month, 30 later · 1 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
and 50 more not named here
sigmoid 51 other papers
9 dated earlier, 1 the same month, 41 later · 2 only as an assembly brick
1505.05770 (2015-05)
Variational Inference with Normalizing Flows
1804.00779 (2018-04)
Neural Autoregressive Flows
1809.10765 (2018-09)
Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection
and 48 more not named here
get_layer_uid 33 other papers
21 dated earlier, 1 the same month, 11 later · 5 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1606.09375 (2016-06)
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
and 30 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Label Propagation (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptually similar, theoretical relation between LPA and GCN has not yet been investigated. Here we study the relationship between LPA and GCN in terms of two aspects: (1) feature/label smoothing where we analyze how the feature/label of one node is spread over its neighbors; And, (2) feature/label influence of how much the initial feature/label of one node influences the final feature/label of another node. Based on our theoretical analysis, we propose an end-to-end model that unifies GCN and LPA for node classification. In our unified model, edge weights are learnable, and the LPA serves as regularization to assist the GCN in learning proper edge weights that lead to improved classification performance. Our model can also be seen as learning attention weights based on node labels, which is more task-oriented than existing feature-based attention models. In a number of experiments on real-world graphs, our model shows superiority over state-of-the-art GCN-based methods in terms of node classification accuracy.

For agents

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

get_harvested_code_for_paper("2002.06755")
get_code_for_paper("2002.06755")
have("2002.06755")

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

curl https://syntology.ai/api/ran/2002.06755.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.06755.svg)](https://syntology.ai/paper/2002.06755)

Connect an agent — have() is free.