SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.13833 · 2023

GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2310.13833.json · badge: /api/ran/2310.13833.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
graph-com/graphmaker canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
edge_list_reindexed Ran
ran, honoured the contract we drafted
graph-com/graphmaker/eval_utils.py
code served (permissive licence) · get_code("c5f70271ef404e19")
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 list, ndim 2, dtype family int; 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 networkx as nx

# Create a simple graph with nodes and edges
G = nx.Graph()
G.add_nodes_from(['a', 'b', 'c', 'd'])
G.add_edges_from([('a', 'b'), ('b', 'c'), ('c', 'd'), ('a', 'd')])

ARGS = {
    'G': G
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — a list 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
get_triangle_count Ran
ran; our contract draft was wrong, not the code
graph-com/graphmaker/eval_utils.py
code served (permissive licence) · get_code("2837a5b5768ade09")
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 networkx as nx

# Create a simple undirected graph with some triangles
nx_g = nx.Graph()

# Add edges to create triangles
# Triangle 1: 0-1-2-0
nx_g.add_edges_from([(0, 1), (1, 2), (2, 0)])

# Triangle 2: 1-3-4-1
nx_g.add_edges_from([(1, 3), (3, 4), (4, 1)])

# Add a non-triangle edge
nx_g.add_edge(5, 6)

ARGS = {
    "nx_g": nx_g
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — 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_train_yaml Ran
ran; our contract draft was wrong, not the code
graph-com/graphmaker/setup_utils.py
code served (permissive licence) · get_code("7965c12e0a39e701")
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 os
import tempfile
import yaml
from pathlib import Path

torch_imported = False
try:
    import torch
    torch.manual_seed(0)
    torch_imported = True
except ImportError:
    pass

# Create temporary directory structure for configs
temp_dir = tempfile.mkdtemp()
configs_dir = Path(temp_dir) / "configs"
configs_dir.mkdir(exist_ok=True)

# Create sample data directories
data_dir_sync = configs_dir / "sample_data_sync"
data_dir_sync.mkdir(exist_ok=True)

data_dir_async = configs_dir / "sample_data_async"
data_dir_async.mkdir(exist_ok=True)

# Create Sync config YAML
sync_config = {
    'meta_data': {
        'variant': 'sync_v1'
    },
    'gnn_X': {
        'hidden_t': 64,
        'hidden_X': 32,
        'hidden_Y': 16,
        'num_gnn_layers': 3,
        'dropout': 0.1
    },
    'gnn_E': {
        'hidden_t': 64,
        'hidden_X': 32,
        'hidden_Y': 16,
        'hidden_E': 24,
        'num_gnn_layers': 3,
        'dropout': 0.1
    },
    'diffusion': {
        'T': 1000
    },
    'optimizer_X': {
        'lr': 0.001,
        'weight_decay': 0.0,
        'amsgrad': False
    },
    'optimizer_E': {
        'lr': 0.001,
        'weight_decay': 0.0,
        'amsgrad': False
    },
    'lr_scheduler': {
        'factor': 0.5,
        'patience': 10,
        'verbose': True
    },
    'train': {
        'num_epochs': 100,
        'val_every_epochs': 5,
        'patient_epochs': 20,
        'max_grad_norm': 1.0,
        'batch_size': 32,
        'val_batch_size': 64
    }
}

# Create Async config YAML
async_config = {
    'meta_data': {
        'variant': 'async_v1'
    },
    'mlp_X': {
        'hidden_t': 48,
        'hidden_X': 32,
        'hidden_Y': 16,
        'num_mlp_layers': 2,
        'dropout': 0.1
    },
    'gnn_E': {
        'hidden_t': 64,
        'hidden_X': 32,
        'hidden_Y': 16,
        'hidden_E': 24,
        'num_gnn_layers': 3,
        'dropout': 0.1
    },
    'diffusion': {
        'T_X': 500,
        'T_E': 750
    },
    'optimizer_X': {
        'lr': 0.001,
        'weight_decay': 0.0,
        'amsgrad': False
    },
    'optimizer_E': {
        'lr': 0.001,
        'weight_decay': 0.0,
        'amsgrad': False
    },
    'lr_scheduler': {
        'factor': 0.5,
        'patience': 10,
        'verbose': True
    },
    'train': {
        'num_epochs': 100,
        'val_every_epochs': 5,
        'patient_epochs': 20,
        'max_grad_norm': 1.0,
        'batch_size': 32,
        'val_batch_size': 64
    }
}

# Write YAML files
with open(data_dir_sync / "train_Sync.yaml", "w") as f:
    yaml.dump(sync_config, f)

with open(data_dir_async / "train_Async.yaml", "w") as f:
    yaml.dump(async_config, f)

# Change to temp directory so relative path works
original_cwd = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    "data_name": "sample_data_sync",
    "model_name": "Sync"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pydantic, torch, yaml — 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
preprocess Not yet run
unverified (harvested, no recorded run)
graph-com/graphmaker/data.py
code served (permissive licence) · get_code("653c9c89c2bda64c")
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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large-scale graphs with node attributes are increasingly common in various real-world applications. Creating synthetic, attribute-rich graphs that mirror real-world examples is crucial, especially for sharing graph data for analysis and developing learning models when original data is restricted to be shared. Traditional graph generation methods are limited in their capacity to handle these complex structures. Recent advances in diffusion models have shown potential in generating graph structures without attributes and smaller molecular graphs. However, these models face challenges in generating large attributed graphs due to the complex attribute-structure correlations and the large size of these graphs. This paper introduces a novel diffusion model, GraphMaker, specifically designed for generating large attributed graphs. We explore various combinations of node attribute and graph structure generation processes, finding that an asynchronous approach more effectively captures the intricate attribute-structure correlations. We also address scalability issues through edge mini-batching generation. To demonstrate the practicality of our approach in graph data dissemination, we introduce a new evaluation pipeline. The evaluation demonstrates that synthetic graphs generated by GraphMaker can be used to develop competitive graph machine learning models for the tasks defined over the original graphs without actually accessing these graphs, while many leading graph generation methods fall short in this evaluation.

For agents

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

get_harvested_code_for_paper("2310.13833")
get_code_for_paper("2310.13833")
have("2310.13833")

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

curl https://syntology.ai/api/ran/2310.13833.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.13833.svg)](https://syntology.ai/paper/2310.13833)

Connect an agent — have() is free.