SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.00077 · 2020

Neural Architecture Search in Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 2 have no contract verdict; 0 failures of our instrument; 1 no recorded run), 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/2008.00077.json · badge: /api/ran/2008.00077.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
mhnnunes/nas_gnn canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
evaluate Ran
ran on a synthesized input
mhnnunes/nas_gnn/graphnas/gnn_model_manager.py
code served (permissive licence) · get_code("20568d7a0cb74f25")
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 float, ndim 0, dtype family float, shape () 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 torch

torch.manual_seed(0)

# Create small tensors for the evaluate function
# output: should have shape (batch_size, num_classes) - function calls torch.max(output, dim=1)
batch_size = 2
num_classes = 4
output = torch.randn(batch_size, num_classes)

# labels: should have shape (batch_size,) - function indexes it with mask
labels = torch.tensor([0, 2])

# mask: should have shape (batch_size,) and be boolean - function uses it for indexing and .sum()
mask = torch.tensor([True, True])

ARGS = {
    "output": output,
    "labels": labels,
    "mask": mask,
}
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 float, ndim 0, dtype family float, shape () — shape () 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
load_data Ran
ran on a synthesized input
mhnnunes/nas_gnn/graphnas_variants/macro_graphnas/pyg/pyg_gnn_model_manager.py
code served (permissive licence) · get_code("52d329a9bdfbfd9b")
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 Data. 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_geometric.transforms as T
from torch_geometric.data import Data

torch.manual_seed(0)

# Create a minimal mock dataset that mimics Planetoid structure
class MockGeometricDataset:
    def __init__(self, num_nodes=2000, num_features=10, num_classes=7):
        self.num_nodes = num_nodes
        self.num_features = num_features
        self.num_classes = num_classes
        
    def __getitem__(self, idx):
        # Create minimal graph data
        edge_index = torch.tensor([[0, 1, 1, 2], [1, 0, 2, 1]], dtype=torch.long)
        x = torch.randn(self.num_nodes, self.num_features)
        y = torch.randint(0, self.num_classes, (self.num_nodes,))
        
        data = Data(x=x, edge_index=edge_index, y=y)
        data.num_nodes = self.num_nodes
        return data

# Monkey-patch the dataset loaders to return our mock
original_planetoid = None
original_coauthor = None
original_amazon = None

def mock_planetoid_init(self, root, name, transform=None):
    self._data = MockGeometricDataset(num_nodes=2000, num_features=10, num_classes=7)

def mock_coauthor_init(self, root, name, transform=None):
    self._data = MockGeometricDataset(num_nodes=2000, num_features=10, num_classes=15)

def mock_amazon_init(self, root, name, transform=None):
    self._data = MockGeometricDataset(num_nodes=2000, num_features=10, num_classes=10)

def mock_getitem(self, idx):
    return self._data[idx]

# Apply patches
import torch_geometric.datasets
torch_geometric.datasets.Planetoid.__init__ = mock_planetoid_init
torch_geometric.datasets.Planetoid.__getitem__ = mock_getitem
torch_geometric.datasets.Coauthor.__init__ = mock_coauthor_init
torch_geometric.datasets.Coauthor.__getitem__ = mock_getitem
torch_geometric.datasets.Amazon.__init__ = mock_amazon_init
torch_geometric.datasets.Amazon.__getitem__ = mock_getitem

ARGS = {
    'dataset': 'Cora',
    'supervised': False,
    'full_data': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Data — a Data 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
gat_message Not yet run
unverified (harvested, no recorded run)
mhnnunes/nas_gnn/graphnas/gnn.py
code served (permissive licence) · get_code("79a91165eceb9b79")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
evaluate 1 other paper
1 dated earlier
1904.09981 (2019-04)
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
gat_message 1 other paper
1 dated earlier
1904.09981 (2019-04)
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning

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

Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes (and edges) follow no absolute order, and it is hard for traditional machine learning (ML) algorithms to recognize a pattern and generalize their predictions on this type of data. Graph Neural Networks (GNN) successfully tackled this problem. They became popular after the generalization of the convolution concept to the graph domain. However, they possess a large number of hyperparameters and their design and optimization is currently hand-made, based on heuristics or empirical intuition. Neural Architecture Search (NAS) methods appear as an interesting solution to this problem. In this direction, this paper compares two NAS methods for optimizing GNN: one based on reinforcement learning and a second based on evolutionary algorithms. Results consider 7 datasets over two search spaces and show that both methods obtain similar accuracies to a random search, raising the question of how many of the search space dimensions are actually relevant to the problem.

For agents

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

get_harvested_code_for_paper("2008.00077")
get_code_for_paper("2008.00077")
have("2008.00077")

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

curl https://syntology.ai/api/ran/2008.00077.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.00077.svg)](https://syntology.ai/paper/2008.00077)

Connect an agent — have() is free.