SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.02133 · ICML · 2020

Simple and Deep Graph Convolutional Networks

Yaliang Li, Bolin Ding, Ming Chen, Zhewei Wei, Zengfeng Huang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 2 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/2007.02133.json · badge: /api/ran/2007.02133.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
chennnM/GCNII canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
DropEdge/DropEdge community
Papers with Code archive
2 ran · 1 no recorded run
tyxxzjpdez/GCNII-DropGroups community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
GCNII Ran
ran on a synthesized input · constructed an object; no result was computed
chennnM/GCNII/model.py
pointer only (licence: NONE) · get_code("a074a40bcfdd0a11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chennnM/GCNII 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.

GCNII Ran
ran on a synthesized input · constructed an object; no result was computed
tyxxzjpdez/GCNII-DropGroups/model.py
pointer only (licence: NONE) · get_code("d20eb9dda5900242")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tyxxzjpdez/GCNII-DropGroups 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.

GraphBaseBlock Ran
ran on a synthesized input · constructed an object; no result was computed
DropEdge/DropEdge/src/layers.py
code served (permissive licence) · get_code("bb5e99ea5619c65c")
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 an instance of its own class, GraphBaseBlock: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import torch.nn.functional as F
import math

torch.manual_seed(0)

# Create tiny test data
num_nodes = 2
in_feat = 4
out_feat = 3
n_layers = 2

# Create a sparse adjacency matrix (num_nodes x num_nodes)
# Using a simple sparse tensor with some connections
indices = torch.LongTensor([[0, 1], [1, 0]]).t()
values = torch.FloatTensor([1.0, 1.0])
adj = torch.sparse.FloatTensor(indices, values, torch.Size([num_nodes, num_nodes]))

ARGS = {
    'in_features': in_feat,
    'out_features': out_feat,
    'nbaselayer': n_layers,
    'withbn': True,
    'withloop': True,
    'activation': F.relu,
    'dropout': 0.5,
    'aggrmethod': 'concat',
    'dense': 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 GraphBaseBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GraphBaseBlock 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
GraphConvolution Ran
ran on a synthesized input · constructed an object; no result was computed
chennnM/GCNII/model.py
pointer only (licence: NONE) · get_code("d25069830e57132b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chennnM/GCNII 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.

GraphConvolutionBS Ran
ran on a synthesized input · constructed an object; no result was computed
DropEdge/DropEdge/src/layers.py
code served (permissive licence) · get_code("d708bae8bd5d1d66")
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 an instance of its own class, GraphConvolutionBS: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import math

torch.manual_seed(0)

# Define a small activation function
def activation_fn(x):
    return torch.relu(x)

# Create the ARGS dictionary for GraphConvolutionBS
ARGS = {
    'in_features': 4,
    'out_features': 3,
    'activation': activation_fn,
    'withbn': True,
    'withloop': True,
    'bias': True,
    'res': False
}

# Optionally, create test data to verify the layer works
if __name__ == "__main__":
    gcn = nn.Module()
    gcn.__class__ = type('GraphConvolutionBS', (nn.Module,), {
        '__init__': lambda self, in_features, out_features, activation=lambda x: x, withbn=True, withloop=True, bias=True, res=False: None
    })
    
    # Create small test tensors
    num_nodes = 2
    input_features = torch.randn(num_nodes, ARGS['in_features'])
    
    # Create a small sparse adjacency matrix
    indices = torch.LongTensor([[0, 1], [1, 0]]).t().contiguous()
    values = torch.FloatTensor([1.0, 1.0])
    adj = torch.sparse.FloatTensor(indices, values, torch.Size([num_nodes, num_nodes]))
    
    print("Input shape:", input_features.shape)
    print("Adjacency matrix shape:", adj.shape)
    print("ARGS:", ARGS)
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 GraphConvolutionBS — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GraphConvolutionBS 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
GraphConvolution Not yet run
unverified (harvested, no recorded run)
tyxxzjpdez/GCNII-DropGroups/model.py
pointer only (licence: NONE) · get_code("a34e675fad092d7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tyxxzjpdez/GCNII-DropGroups 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. No invocation recorded.

ResGCNBlock Not yet run
unverified (harvested, no recorded run)
DropEdge/DropEdge/src/layers.py
code served (permissive licence) · get_code("9fab06aa18273efc")
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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
GraphConvolution
brick of this paper's assembly: model
1 other paper
1 later
2107.06779 (2021-07)
MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation

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) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the over-smoothing problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: Initial residual and Identity mapping. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi-and fullsupervised tasks. Code is available at https: //github.com/chennnM/GCNII.

For agents

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

get_harvested_code_for_paper("2007.02133")
get_code_for_paper("2007.02133")
have("2007.02133")

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

curl https://syntology.ai/api/ran/2007.02133.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.02133.svg)](https://syntology.ai/paper/2007.02133)

Connect an agent — have() is free.