SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.03348 · 2021

Global Self-Attention as a Replacement for Graph Convolution

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 1 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/2108.03348.json · badge: /api/ran/2108.03348.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
shamim-hussain/egt canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
import_object Ran
ran on a synthesized input
shamim-hussain/egt/lib/training/importer.py
code served (permissive licence) · get_code("23012f87aaa39c42")
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 importlib

def import_object(object_name):
    module_name, object_name = object_name.rsplit('.', 1)
    imported_module = importlib.import_module(module_name)
    return getattr(imported_module, object_name)

# The function takes a dotted path string and imports the object it refers to.
# We need to provide a valid object_name that can be split on the last dot
# into a module name and an object name.

ARGS = {
    'object_name': 'os.path.join'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
import_scheme Ran
ran on a synthesized input
shamim-hussain/egt/lib/training/importer.py
code served (permissive licence) · get_code("ca5300d8a50237fe")
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 MockScheme. 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 importlib
import sys
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a minimal mock scheme module structure
class MockScheme:
    def __init__(self):
        self.name = "test_scheme"
    
    def __call__(self, *args, **kwargs):
        return self

# Create mock modules
mock_scheme_module = MagicMock()
mock_scheme_module.SCHEME = MockScheme()

mock_schemes_package = MagicMock()
sys.modules['lib.training.schemes.test_scheme'] = mock_scheme_module
sys.modules['lib.training.schemes'] = mock_schemes_package
sys.modules['lib.training'] = MagicMock()
sys.modules['lib'] = MagicMock()

# The function import_scheme takes a scheme_name parameter
# It constructs 'lib.training.schemes.' + scheme_name + '.SCHEME'
# and calls import_object on it
# import_object expects a fully qualified name like 'module.path.ClassName'

ARGS = {
    'scheme_name': 'test_scheme'
}
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 MockScheme — a MockScheme output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockScheme 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
read_config_from_file Ran
ran on a synthesized input
shamim-hussain/egt/lib/training/training_base.py
code served (permissive licence) · get_code("4b0f182cd45413d3")
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 json
import tempfile
import os

# Create a temporary config file with valid JSON content
temp_dir = tempfile.gettempdir()
config_file = os.path.join(temp_dir, "test_config.json")

# Write a sample config to the temporary file
sample_config = {
    "model": "bert",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(config_file, 'w') as fp:
    json.dump(sample_config, fp)

ARGS = {
    "config_file": config_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
save_config_to_file Not yet run
unverified (harvested, no recorded run)
shamim-hussain/egt/lib/training/training_base.py
code served (permissive licence) · get_code("219b23ce1676877d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

We propose an extension to the transformer neural network architecture for general-purpose graph learning by adding a dedicated pathway for pairwise structural information, called edge channels. The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data. Our model exclusively uses global self-attention as an aggregation mechanism rather than static localized convolutional aggregation. This allows for unconstrained long-range dynamic interactions between nodes. Moreover, the edge channels allow the structural information to evolve from layer to layer, and prediction tasks on edges/links can be performed directly from the output embeddings of these channels. We verify the performance of EGT in a wide range of graph-learning experiments on benchmark datasets, in which it outperforms Convolutional/Message-Passing Graph Neural Networks. EGT sets a new state-of-the-art for the quantum-chemical regression task on the OGB-LSC PCQM4Mv2 dataset containing 3.8 million molecular graphs. Our findings indicate that global self-attention based aggregation can serve as a flexible, adaptive and effective replacement of graph convolution for general-purpose graph learning. Therefore, convolutional local neighborhood aggregation is not an essential inductive bias.

For agents

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

get_harvested_code_for_paper("2108.03348")
get_code_for_paper("2108.03348")
have("2108.03348")

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

curl https://syntology.ai/api/ran/2108.03348.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.03348.svg)](https://syntology.ai/paper/2108.03348)

Connect an agent — have() is free.