SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.07331 · 2020

Knowledge Embedding Based Graph Convolutional Network

arXiv · PDF · Open in the Atlas

Code that ran

5 of 12 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 2 have no contract verdict; 2 failures of our instrument; 7 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/2006.07331.json · badge: /api/ran/2006.07331.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
Maysir/GEM-GCN canonical (classifier label)
classifier basis: census
5 ran · 7 no recorded run
FunctionStatusWhere it lives
construct_feed_dict Ran
ran on a synthesized input
Maysir/GEM-GCN/utils.py
code served (permissive licence) · get_code("3eee20dd95f3f8d9")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a simple placeholder class to simulate TensorFlow-style placeholders
class Placeholder:
    def __init__(self, name):
        self.name = name
    
    def __repr__(self):
        return f"Placeholder({self.name})"
    
    def __hash__(self):
        return hash(self.name)
    
    def __eq__(self, other):
        return isinstance(other, Placeholder) and self.name == other.name

# Create features tensor (batch_size=2, feature_dim=4)
features = torch.randn(2, 4)

# Create support as a list of lists (nested structure)
# This tests the isinstance(support[0], list) branch
support = [
    [torch.randn(3, 4), torch.randn(3, 4)],  # First layer: 2 support matrices
    [torch.randn(3, 4), torch.randn(3, 4)],  # Second layer: 2 support matrices
]

# Create placeholders dict
# The function expects:
# - placeholders['features']: a placeholder for features
# - placeholders['support']: a list of placeholders (one per support layer)
#   where each element can be either:
#   - a single placeholder (if support is flat list)
#   - a list of placeholders (if support is list of lists)

placeholders = {
    'features': Placeholder('features'),
    'support': [
        [Placeholder('support_0_0'), Placeholder('support_0_1')],  # Layer 0: 2 placeholders
        [Placeholder('support_1_0'), Placeholder('support_1_1')],  # Layer 1: 2 placeholders
    ]
}

ARGS = {
    'features': features,
    'support': support,
    'placeholders': placeholders,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
dot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Maysir/GEM-GCN/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from thumlp/tensorgcn, is pointer only (licence: NONE) · get_code("bc3a2072a2a9cca3")
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 thumlp/tensorgcn, 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.

get_layer_uid Ran
ran, honoured the contract we drafted
Maysir/GEM-GCN/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from thumlp/tensorgcn, is pointer only (licence: NONE) · get_code("b82968db452628fd")
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 thumlp/tensorgcn, 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.

inverse_sum Ran
ran on a synthesized input
Maysir/GEM-GCN/utils.py
code served (permissive licence) · get_code("6d6bc974d65d3d0c")
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 ndarray, ndim 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:27Z. 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
import scipy.sparse as sp

# Construct a small sparse adjacency matrix
# The function expects a matrix-like object that can be converted to coo_matrix
# and supports sum(1) operation (row sums)

# Create a small 4x4 sparse adjacency matrix
rows = np.array([0, 1, 2, 3, 0, 2])
cols = 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, (rows, cols)), shape=(4, 4))

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 ndarray, ndim 2, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Maysir/GEM-GCN/inits.py
pointer only (licence: MIT); the stored copy get_code serves, from nju-websoft/OpenEA, is pointer only (licence: GPL-3.0) · get_code("0a0766dae72ea646")
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 nju-websoft/OpenEA, 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.

align_loss Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/metrics.py
code served (permissive licence) · get_code("37e5d6d0a672c228")
How it ran

no invocation recorded.

class_loss Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/metrics.py
code served (permissive licence) · get_code("618a034107283e1f")
How it ran

no invocation recorded.

get_placeholder_by_name Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/metrics.py
code served (permissive licence) · get_code("8e65d91b0b6a8a69")
How it ran

no invocation recorded.

glorot Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/inits.py
code served (permissive licence) · get_code("aa622c9b6b2d0332")
How it ran

no invocation recorded.

preprocess_adj Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/utils.py
code served (permissive licence) · get_code("a3b7442294809e8a")
How it ran

no invocation recorded.

sparse_dropout Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from thumlp/tensorgcn, is pointer only (licence: NONE) · get_code("81be8a5f4732fe52")
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 thumlp/tensorgcn, 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. No invocation recorded.

uniform Not yet run
unverified (harvested, no recorded run)
Maysir/GEM-GCN/inits.py
code served (permissive licence) · get_code("aa7d8441fcd40dbf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 6 the same month, 6 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
get_layer_uid 33 other papers
24 dated earlier, 1 the same month, 8 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
sparse_dropout 18 other papers
13 dated earlier, 1 the same month, 4 later · 2 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 15 more not named here
zeros 18 other papers
11 dated earlier, 2 the same month, 5 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 15 more not named here
dot 17 other papers
12 dated earlier, 1 the same month, 4 later · 3 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 14 more not named here
uniform 17 other papers
11 dated earlier, 2 the same month, 4 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 14 more not named here
glorot 16 other papers
10 dated earlier, 1 the same month, 5 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 13 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

Recently, a considerable literature has grown up around the theme of Graph Convolutional Network (GCN). How to effectively leverage the rich structural information in complex graphs, such as knowledge graphs with heterogeneous types of entities and relations, is a primary open challenge in the field. Most GCN methods are either restricted to graphs with a homogeneous type of edges (e.g., citation links only), or focusing on representation learning for nodes only instead of jointly propagating and updating the embeddings of both nodes and edges for target-driven objectives. This paper addresses these limitations by proposing a novel framework, namely the Knowledge Embedding based Graph Convolutional Network (KE-GCN), which combines the power of GCNs in graph-based belief propagation and the strengths of advanced knowledge embedding (a.k.a. knowledge graph embedding) methods, and goes beyond. Our theoretical analysis shows that KE-GCN offers an elegant unification of several well-known GCN methods as specific cases, with a new perspective of graph convolution. Experimental results on benchmark datasets show the advantageous performance of KE-GCN over strong baseline methods in the tasks of knowledge graph alignment and entity classification.

For agents

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

get_harvested_code_for_paper("2006.07331")
get_code_for_paper("2006.07331")
have("2006.07331")

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

curl https://syntology.ai/api/ran/2006.07331.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.07331.svg)](https://syntology.ai/paper/2006.07331)

Connect an agent — have() is free.