SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.13583 · 2023

Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns

arXiv · PDF · Open in the Atlas

Code that ran

13 of 13 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 8 failures of our instrument; 0 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/2312.13583.json · badge: /api/ran/2312.13583.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
zjunet/G-Tuning canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
FunctionStatusWhere it lives
align_graphs Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/methods/learner.py
pointer only (licence: NONE); the stored copy get_code serves, from caoyxuan/w2pgnn, is pointer only (licence: NONE) · get_code("d894f2c5cbab6c96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

distance_matrix Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/ot_distance.py
pointer only (licence: NONE) · get_code("8f6a0627aad6b737")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

distance_tensor Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/ot_distance.py
pointer only (licence: NONE) · get_code("2b819d2bb1b0bcdb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

estimate_target_distribution Ran
ran, honoured the contract we drafted
zjunet/G-Tuning/GCC-based/methods/learner.py
pointer only (licence: NONE); the stored copy get_code serves, from caoyxuan/w2pgnn, is pointer only (licence: NONE) · get_code("6faf9171aaf972ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

graph_numpy2tensor Ran
ran, violated the contract we drafted
zjunet/G-Tuning/GCC-based/methods/learner.py
pointer only (licence: NONE); the stored copy get_code serves, from caoyxuan/w2pgnn, is pointer only (licence: NONE) · get_code("45f3526206f9a0f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gw_distance Ran
ran, violated the contract we drafted
zjunet/G-Tuning/GCC-based/methods/simulator.py
pointer only (licence: NONE) · get_code("c0c6de6502f72024")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

option_update Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/train_G_Tuning.py
pointer only (licence: NONE) · get_code("1df7f49664c77c5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sampling_gaussian Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/model.py
pointer only (licence: NONE) · get_code("1fa699677ecc4d72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sampling_gmm Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/model.py
pointer only (licence: NONE) · get_code("9b58c30cbb07b507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

simulate_graphs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zjunet/G-Tuning/GCC-based/methods/simulator.py
pointer only (licence: NONE) · get_code("2ded63c00749fb47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sum_matrix Ran
ran; our contract draft was wrong, not the code
zjunet/G-Tuning/GCC-based/ot_distance.py
pointer only (licence: NONE) · get_code("08bfd3fe7445ab40")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

synthesize_graphon Ran
ran, honoured the contract we drafted
zjunet/G-Tuning/GCC-based/methods/simulator.py
pointer only (licence: NONE) · get_code("3c505c6193699765")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

test_moco Ran
ran, honoured the contract we drafted
zjunet/G-Tuning/GCC-based/generate.py
pointer only (licence: NONE); the stored copy get_code serves, from galina0217/apt, is pointer only (licence: NONE) · get_code("48d3912bc3a7d2b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zjunet/G-Tuning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 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
graph_numpy2tensor 2 other papers
1 dated earlier, 1 later
2303.16458 (2023-03)
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
2401.09953 (2024-01)
Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
align_graphs 1 other paper
1 dated earlier
2303.16458 (2023-03)
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
distance_tensor 1 other paper
1 dated earlier
2002.02913 (2020-02)
Learning Autoencoders with Relational Regularization
estimate_target_distribution 1 other paper
1 dated earlier
2303.16458 (2023-03)
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
sum_matrix 1 other paper
1 dated earlier
2002.02913 (2020-02)
Learning Autoencoders with Relational Regularization
test_moco 1 other paper
1 dated earlier
2311.01038 (2023-11)
Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks

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

Recently, the paradigm of pre-training and fine-tuning graph neural networks has been intensively studied and applied in a wide range of graph mining tasks. Its success is generally attributed to the structural consistency between pre-training and downstream datasets, which, however, does not hold in many real-world scenarios. Existing works have shown that the structural divergence between pre-training and downstream graphs significantly limits the transferability when using the vanilla fine-tuning strategy. This divergence leads to model overfitting on pre-training graphs and causes difficulties in capturing the structural properties of the downstream graphs. In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs. Furthermore, we propose G-Tuning to preserve the generative patterns of downstream graphs. Given a downstream graph G, the core idea is to tune the pre-trained GNN so that it can reconstruct the generative patterns of G, the graphon W. However, the exact reconstruction of a graphon is known to be computationally expensive. To overcome this challenge, we provide a theoretical analysis that establishes the existence of a set of alternative graphons called graphon bases for any given graphon. By utilizing a linear combination of these graphon bases, we can efficiently approximate W. This theoretical finding forms the basis of our proposed model, as it enables effective learning of the graphon bases and their associated coefficients. Compared with existing algorithms, G-Tuning demonstrates an average improvement of 0.5% and 2.6% on in-domain and out-of-domain transfer learning experiments, respectively.

For agents

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

get_harvested_code_for_paper("2312.13583")
get_code_for_paper("2312.13583")
have("2312.13583")

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

curl https://syntology.ai/api/ran/2312.13583.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.13583.svg)](https://syntology.ai/paper/2312.13583)

Connect an agent — have() is free.