SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.09609 · 2022

SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 4 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/2210.09609.json · badge: /api/ran/2210.09609.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
MindCode-4/code-9 community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
labels2cat Ran
ran on a synthesized input
MindCode-4/code-9/Three-Dimensional-Lip-Motion-Network-for-Text-Independent-Speaker-Recognition-master/3LMNet_ms.py
code served (permissive licence) · get_code("fc721854c3bf3762")
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 1, dtype family int, shape (3,) 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.

from sklearn.preprocessing import LabelEncoder
import numpy as np

# Create a label encoder and fit it with some sample labels
label_encoder = LabelEncoder()
sample_labels = ['cat', 'dog', 'cat', 'bird', 'dog']
label_encoder.fit(sample_labels)

# Create a list of labels to transform
list_to_transform = ['cat', 'dog', 'bird']

ARGS = {
    'label_encoder': label_encoder,
    'list': list_to_transform
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (3,) — shape (3,) 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
labels2onehot Ran
ran on a synthesized input
MindCode-4/code-9/Three-Dimensional-Lip-Motion-Network-for-Text-Independent-Speaker-Recognition-master/3LMNet_ms.py
code served (permissive licence) · get_code("962937e4c560ebb3")
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 (3, 3) 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
from sklearn.preprocessing import LabelEncoder, OneHotEncoder

# Create sample categorical data
sample_labels = np.array(['cat', 'dog', 'cat', 'bird', 'dog'])

# Initialize and fit LabelEncoder
label_encoder = LabelEncoder()
label_encoder.fit(sample_labels)

# Initialize and fit OneHotEncoder
one_hot_encoder = OneHotEncoder(sparse_output=False)
# OneHotEncoder needs 2D input for fitting
one_hot_encoder.fit(label_encoder.transform(sample_labels).reshape(-1, 1))

# Create test input list
test_list = np.array(['cat', 'dog', 'bird'])

ARGS = {
    'OneHotEncoder': one_hot_encoder,
    'label_encoder': label_encoder,
    'list': test_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 (3, 3) — shape (3, 3) 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
onehot2labels Ran
ran on a synthesized input
MindCode-4/code-9/Three-Dimensional-Lip-Motion-Network-for-Text-Independent-Speaker-Recognition-master/3LMNet_ms.py
code served (permissive licence) · get_code("9c1b2df7fb7a5f6f")
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 1, dtype family float; 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 numpy as np
from sklearn.preprocessing import LabelEncoder

# Create a LabelEncoder with some sample classes
label_encoder = LabelEncoder()
label_encoder.fit(['cat', 'dog', 'bird', 'fish'])

# Create a one-hot encoded array with shape (2, 4)
# 2 samples, 4 classes
y_onehot = np.array([
    [1, 0, 0, 0],  # sample 0: class 'cat'
    [0, 0, 1, 0]   # sample 1: class 'bird'
])

ARGS = {
    'label_encoder': label_encoder,
    'y_onehot': y_onehot
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 float — 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
pendulum Ran
ran on a synthesized input
MindCode-4/code-9/SciNet/utils.py
code served (permissive licence) · get_code("8de727761d866421")
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 float64, ndim 0, dtype family float; 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 numpy as np

ARGS = {
    't': 1.5,
    'A0': 2.0,
    'delta0': 0.5,
    'k': 10.0,
    'b': 1.0,
    'm': 1.0
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
anet1 Not yet run
unverified (harvested, no recorded run)
MindCode-4/code-9/Two-Layer-ReLU-Network-Analytically/anmin.py
code served (permissive licence) · get_code("9a0dfd5a0f02da54")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
labels2cat 4 other papers
4 later
2212.08663 (2022-12)
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
2305.03045 (2023-05)
OctFormer: Octree-based Transformers for 3D Point Clouds
2306.01116 (2023-06)
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
and 1 more not named here
labels2onehot 4 other papers
4 later
2212.08663 (2022-12)
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
2305.03045 (2023-05)
OctFormer: Octree-based Transformers for 3D Point Clouds
2306.01116 (2023-06)
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
and 1 more not named here
onehot2labels 4 other papers
4 later
2212.08663 (2022-12)
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
2305.03045 (2023-05)
OctFormer: Octree-based Transformers for 3D Point Clouds
2306.01116 (2023-06)
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
and 1 more not named here
pendulum 4 other papers
4 later
2212.08663 (2022-12)
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
2305.06329 (2023-05)
Similarity of Neural Network Models: A Survey of Functional and Representational Measures
2306.01116 (2023-06)
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
and 1 more not named here
anet1 3 other papers
3 later
2212.08663 (2022-12)
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
2305.03045 (2023-05)
OctFormer: Octree-based Transformers for 3D Point Clouds
2311.15127 (2023-11)
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

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

The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause inference latency when deploying GNNs to large-scale graphs. One promising inference acceleration direction is to distill the GNNs into message-passing-free student multi-layer perceptrons (MLPs). However, the MLP student cannot fully learn the structure knowledge due to the lack of structure inputs, which causes inferior performance in the heterophily and inductive scenarios. To address this, we intend to inject structure information into MLP-like students in low-latency and interpretable ways. Specifically, we first design a Structure-Aware MLP (SA-MLP) student that encodes both features and structures without message-passing. Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information. Furthermore, we design a latent structure embedding approximation technique with two-stage distillation for inductive scenarios. Extensive experiments on eight benchmark datasets under both transductive and inductive settings show that our SA-MLP can consistently outperform the teacher GNNs, while maintaining faster inference as MLPs. The source code of our work can be found in https://github.com/JC-202/SA-MLP.

For agents

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

get_harvested_code_for_paper("2210.09609")
get_code_for_paper("2210.09609")
have("2210.09609")

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

curl https://syntology.ai/api/ran/2210.09609.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.09609.svg)](https://syntology.ai/paper/2210.09609)

Connect an agent — have() is free.