SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.04987 · ICLR · 2021

AutoGL: A Library for Automated Graph Learning

Heng Chang, Wenwu Zhu, Xin Wang, Ziwei Zhang, Yijian Qin, Zeyang Zhang, Chaoyu Guan, Jie Cai, Jiyan Jiang, Haoyang Li, Zixin Sun, Beini Xie, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/2104.04987.json · badge: /api/ran/2104.04987.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
THUMNLab/AutoGL canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
THUMNLab/AutoGL-light canonical (classifier label)
classifier basis: census
0 ran · 1 no recorded run
thumnlab/autogl-light extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
data_is_numpy Ran
ran, violated the contract we drafted
THUMNLab/AutoGL/autogl/module/_feature/utils.py
code served (permissive licence) · get_code("c235ed1eba8c446e")
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 bool, 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 numpy as np

class MockData:
    def __init__(self, x):
        self.x = x

# Create a small numpy array for the x attribute
x_data = np.array([[1.0, 2.0, 3.0, 4.0],
                    [5.0, 6.0, 7.0, 8.0]])

# Create the data object with numpy array
data = MockData(x_data)

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
data_is_tensor Ran
ran, violated the contract we drafted
THUMNLab/AutoGL/autogl/module/_feature/utils.py
code served (permissive licence) · get_code("6624e068d14e7847")
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 bool, 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)

# The function checks if data.x is a torch.Tensor
# So we need an object with an 'x' attribute that is a torch.Tensor

class MockData:
    def __init__(self, x):
        self.x = x

# Create a small tensor
x_tensor = torch.randn(2, 4)

# Create the data object
data = MockData(x=x_tensor)

ARGS = {
    "data": data
}
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 bool, 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
data_tensor2np Ran
ran; our contract draft was wrong, not the code
THUMNLab/AutoGL/autogl/module/_feature/utils.py
code served (permissive licence) · get_code("b77834b241fcd9a1")
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 MockData. 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

torch.manual_seed(0)

class MockData:
    """Mock data object that mimics a graph data structure with x, y, edge_index attributes."""
    def __init__(self, x, y, edge_index):
        self.x = x
        self.y = y
        self.edge_index = edge_index

# Create small tensors with distinct sizes
x_tensor = torch.randn(2, 4)  # 2 nodes, 4 features
y_tensor = torch.randint(0, 2, (2,))  # 2 labels
edge_index_tensor = torch.tensor([[0, 1], [1, 0]], dtype=torch.long)  # 2x2 edge index

# Create the data object with tensor attributes
data = MockData(
    x=x_tensor,
    y=y_tensor,
    edge_index=edge_index_tensor
)

ARGS = {
    "data": data
}
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 MockData — a MockData output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockData 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
onek_encoding_unk Ran
ran, honoured the contract we drafted
thumnlab/autogl-light/example/GNNUQ_NAS/gnn_uq/data_utils.py
code served (permissive licence) · get_code("2af7097265be5bad")
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) and returned list, ndim 1, 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - value: a single item that may or may not be in choices
# - choices: a list-like object that supports .index() method and 'in' operator

# Create test arguments
value = "apple"
choices = ["apple", "banana", "orange", "grape"]

ARGS = {
    "value": value,
    "choices": choices
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
op_max Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THUMNLab/AutoGL/autogl/module/_feature/auto_feature.py
code served (permissive licence) · get_code("2cf65744b912b5c2")
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, shape (2, 4) 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 numpy as np

# Analyze the function:
# - x: a numpy array that supports indexing and np.max
# - nbs: a list/sequence of neighbor indices (each element is an indexable collection)
# - The function iterates through nbs, gets neighbors for each u, and computes max along axis 0

# Create sample data
x = np.random.randn(2, 4)  # batch_size=2, feature_dim=4

# nbs should be a list where each element contains indices into x
# Element 0: neighbors are indices [0, 1]
# Element 1: neighbors are index [1]
nbs = [
    np.array([0, 1]),
    np.array([1])
]

ARGS = {
    "x": x,
    "nbs": nbs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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, shape (2, 4) — shape (2, 4) 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
f Not yet run
unverified (harvested, no recorded run)
THUMNLab/AutoGL-light/autogllight/hpo/base.py
code served (permissive licence) · get_code("60ea3d41f4acf8b1")
How it ran

no invocation recorded.

op_mean Not yet run
unverified (harvested, no recorded run)
THUMNLab/AutoGL/autogl/module/_feature/auto_feature.py
code served (permissive licence) · get_code("4de0896322d3d8ed")
How it ran

no invocation recorded.

op_sum Not yet run
unverified (harvested, no recorded run)
THUMNLab/AutoGL/autogl/module/_feature/auto_feature.py
code served (permissive licence) · get_code("e5f9bc5afdc81023")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 7 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
onek_encoding_unk 2 other papers
2 later
2311.04419 (2023-11)
PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids
2410.09290 (2024-10)
Ranking over Regression for Bayesian Optimization and Molecule Selection

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

Recent years have witnessed an upsurge in research interests and applications of machine learning on graphs. However, manually designing the optimal machine learning algorithms for different graph datasets and tasks is inflexible, labor-intensive, and requires expert knowledge, limiting its adaptivity and applicability. Automated machine learning (AutoML) on graphs, aiming to automatically design the optimal machine learning algorithm for a given graph dataset and task, has received considerable attention. However, none of the existing libraries can fully support AutoML on graphs. To fill this gap, we present Automated Graph Learning (AutoGL), the first dedicated library for automated machine learning on graphs. AutoGL is open-source, easy to use, and flexible to be extended. Specifically, we propose a three-layer architecture, consisting of backends to interface with devices, a complete automated graph learning pipeline, and supported graph applications. The automated machine learning pipeline further contains five functional modules: auto feature engineering, neural architecture search, hyper-parameter optimization, model training, and auto ensemble, covering the majority of existing AutoML methods on graphs. For each module, we provide numerous state-of-the-art methods and flexible base classes and APIs, which allow easy usage and customization. We further provide experimental results to showcase the usage of our AutoGL library. We also present AutoGL-light, a lightweight version of AutoGL to facilitate customizing pipelines and enriching applications, as well as benchmarks for graph neural architecture search. The codes of AutoGL are publicly available at https://github.com/THUMNLab/AutoGL.

For agents

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

get_harvested_code_for_paper("2104.04987")
get_code_for_paper("2104.04987")
have("2104.04987")

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

curl https://syntology.ai/api/ran/2104.04987.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.04987.svg)](https://syntology.ai/paper/2104.04987)

Connect an agent — have() is free.