SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.07153 · 2019

Simplifying Graph Convolutional Networks

Tianyi Zhang, Kilian Weinberger, Tao Yu, Christopher Fifty, Felix Wu, Amauri Holanda De Souza

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 2 honoured the contract we drafted, 0 violated it and 5 have 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/1902.07153.json · badge: /api/ran/1902.07153.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
Tiiiger/SGC canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran, honoured the contract we drafted
Tiiiger/SGC/metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from TianxiangZhao/GraphSmote, is pointer only (licence: NONE) · get_code("18557871f0c93b3f")
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 TianxiangZhao/GraphSmote, 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.

aug_normalized_adjacency Ran
ran on a synthesized input
Tiiiger/SGC/normalization.py
code served (permissive licence) · get_code("a4a8c0e8d8c8a86e")
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 coo_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 adjacency matrix
# Using a 4x4 matrix for small size
n_nodes = 4
# Create a simple sparse matrix (not too dense)
row = np.array([0, 1, 2, 3, 0, 2])
col = np.array([1, 2, 3, 0, 3, 1])
data = np.array([1.0, 1.0, 1.0, 1.0, 1.0, 1.0])
adj = sp.coo_matrix((data, (row, col)), shape=(n_nodes, n_nodes))

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 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type coo_matrix — a coo_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a coo_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
f1 Ran
ran on a synthesized input
Tiiiger/SGC/metrics.py
code served (permissive licence) · get_code("cc1fd8ffd02dab36")
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, ndim 1, 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 torch
import numpy as np
from sklearn.metrics import f1_score

torch.manual_seed(0)

# Create a small batch of outputs and labels
batch_size = 2
num_classes = 4

# output: tensor that supports .max(1)[1] to get predictions
# Shape: (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# labels: tensor that can be converted to numpy
# Shape: (batch_size,) with class indices from 0 to num_classes-1
labels = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "output": output,
    "labels": labels,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
fetch_normalization Ran
ran on a synthesized input
Tiiiger/SGC/normalization.py
code served (permissive licence) · get_code("cbd567cd870e332a")
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 function. 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 adjacency matrix
# Using a 4x4 matrix for a small graph
adj_data = np.array([0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0])
adj_dense = adj_data.reshape(4, 4)
adj = sp.csr_matrix(adj_dense)

ARGS = {
    'type': 'AugNormAdj'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
get_model Ran
ran on a synthesized input
Tiiiger/SGC/models.py
code served (permissive licence) · get_code("c6e6b26c7f2a5617")
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 GCN. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import math

torch.manual_seed(0)

ARGS = {
    'model_opt': 'GCN',
    'nfeat': 4,
    'nclass': 3,
    'nhid': 8,
    'dropout': 0.5,
    'cuda': False
}
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 GCN — a GCN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GCN 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
Tiiiger/SGC/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from DSL-Lab/Specformer, is pointer only (licence: GPL-3.0) · get_code("c1d6392f89c5e495")
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 DSL-Lab/Specformer, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

row_normalize Ran
ran on a synthesized input
Tiiiger/SGC/normalization.py
code served (permissive licence) · get_code("9fe90a5693925ebb")
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
# Using a 4x3 sparse matrix with some non-zero values
row = np.array([0, 0, 1, 2, 2, 3])
col = np.array([0, 1, 2, 0, 1, 2])
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
mx = sp.csr_matrix((data, (row, col)), shape=(4, 3))

ARGS = {
    "mx": mx
}
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
sparse_mx_to_torch_sparse_tensor Ran
ran; our contract draft was wrong, not the code
Tiiiger/SGC/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

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, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 5 later) and 3 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
12 dated earlier, 1 the same month, 40 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
sparse_mx_to_torch_sparse_tensor 32 other papers
1 dated earlier, 31 later · 4 only as an assembly brick
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
2002.01633 (2020-02)
Structural Deep Clustering Network
2004.01899 (2020-04)
A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
and 29 more not named here
accuracy 14 other papers
14 later
1905.09550 (2019-05)
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
2002.07128 (2020-02)
Disease State Prediction From Single-Cell Data Using Graph Attention Networks
2103.08826 (2021-03)
GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
and 11 more not named here
aug_normalized_adjacency 1 other paper
1 later
1905.09550 (2019-05)
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
f1 1 other paper
1 later
1905.09550 (2019-05)
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

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

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

For agents

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

get_harvested_code_for_paper("1902.07153")
get_code_for_paper("1902.07153")
have("1902.07153")

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

curl https://syntology.ai/api/ran/1902.07153.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.07153.svg)](https://syntology.ai/paper/1902.07153)

Connect an agent — have() is free.