SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.07225 · AAAI · 2024

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

Qiang Liu, Liang Wang, Shu Wu, Xiang Tao

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 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/2402.07225.json · badge: /api/ran/2402.07225.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
AzureLeon1/AUG-MAE canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
AzureLeon1/AUG-MAE/augmae/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from LiuXiaoxuanPKU/GACT-ICML, is pointer only (licence: NONE) · get_code("adf3b9c6c22af5ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

create_activation Ran
ran; our contract draft was wrong, not the code
AzureLeon1/AUG-MAE/augmae/utils.py
pointer only (licence: NONE) · get_code("9d7dd278d1589149")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

evaluate_graph_embeddings_using_svm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AzureLeon1/AUG-MAE/main_graph.py
pointer only (licence: NONE); the stored copy get_code serves, from thudm/graphmae, is pointer only (licence: NONE) · get_code("0fa9e6c975030f82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

get_current_lr Ran
ran, honoured the contract we drafted
AzureLeon1/AUG-MAE/augmae/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from ZiyanLiu16/MUGEN, is pointer only (licence: NONE) · get_code("c9c9174dc014b586")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

mutli_graph_linear_evaluation Ran
ran, honoured the contract we drafted
AzureLeon1/AUG-MAE/main_inductive.py
pointer only (licence: NONE); the stored copy get_code serves, from thudm/graphmae, is pointer only (licence: NONE) · get_code("54afeb75d9c9c38c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

neg_sce_loss Ran
ran; our contract draft was wrong, not the code
AzureLeon1/AUG-MAE/augmae/models/loss_func.py
pointer only (licence: NONE) · get_code("2818bdcecd25caa5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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.

sce_loss Ran
ran; our contract draft was wrong, not the code
AzureLeon1/AUG-MAE/augmae/models/loss_func.py
pointer only (licence: NONE); the stored copy get_code serves, from ZiyanLiu16/MUGEN, is pointer only (licence: NONE) · get_code("6f9bb5eb98ec4887")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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_classification_evaluation Not yet run
unverified (harvested, no recorded run)
AzureLeon1/AUG-MAE/main_graph.py
pointer only (licence: NONE); the stored copy get_code serves, from thudm/graphmae, is pointer only (licence: NONE) · get_code("1161f390005c518d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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. No invocation recorded.

sig_loss Not yet run
unverified (harvested, no recorded run)
AzureLeon1/AUG-MAE/augmae/models/loss_func.py
pointer only (licence: NONE); the stored copy get_code serves, from ZiyanLiu16/MUGEN, is pointer only (licence: NONE) · get_code("f2502a1d225b3dd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AzureLeon1/AUG-MAE 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 6 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
accuracy 6 other papers
3 dated earlier, 1 the same month, 2 later
2206.11357 (2022-06)
GACT: Activation Compressed Training for Generic Network Architectures
2304.04779 (2023-04)
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
2310.10362 (2023-10)
Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks
and 3 more not named here
sce_loss 6 other papers
3 dated earlier, 1 the same month, 2 later
2304.04779 (2023-04)
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
2309.04589 (2023-09)
Motif-aware Attribute Masking for Molecular Graph Pre-training
2310.00800 (2023-10)
GRAPHPATCHER: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
and 3 more not named here
get_current_lr 4 other papers
1 dated earlier, 1 the same month, 2 later
2304.04779 (2023-04)
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
2402.13630 (2024-02)
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
2410.13798 (2024-10)
Learning Graph Quantized Tokenizers
and 1 more not named here
create_activation 2 other papers
2 later
2404.15806 (2024-04)
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
2603.00143 (2026-03)
GrapHist: Graph Self-Supervised Learning for Histopathology
evaluate_graph_embeddings_using_svm 2 other papers
1 dated earlier, 1 later
2205.10803 (2022-05)
GraphMAE: Self-Supervised Masked Graph Autoencoders
2404.15806 (2024-04)
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
sig_loss 2 other papers
1 the same month, 1 later
2402.13630 (2024-02)
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
2609.00696 (2026-09)
MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks
graph_classification_evaluation 1 other paper
1 dated earlier
2205.10803 (2022-05)
GraphMAE: Self-Supervised Masked Graph Autoencoders
mutli_graph_linear_evaluation 1 other paper
1 dated earlier
2205.10803 (2022-05)
GraphMAE: Self-Supervised Masked Graph Autoencoders

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

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past few years, but the recent advent of graph masked autoencoder (Graph-MAE) rekindles the momentum behind generative methods. Despite the empirical success of GraphMAE, there is still a dearth of theoretical understanding regarding its efficacy. Moreover, while both generative and contrastive methods have been shown to be effective, their connections and differences have yet to be thoroughly investigated. Therefore, we theoretically build a bridge between GraphMAE and GCL, and prove that the node-level reconstruction objective in GraphMAE implicitly performs context-level GCL. Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL. We point out that GraphMAE's alignment performance is restricted by the masking strategy, and the uniformity is not strictly guaranteed. To remedy the aforementioned limitations, we propose an Alignment-Uniformity enhanced Graph Masked AutoEncoder, named AUG-MAE. Specifically, we propose an easyto-hard adversarial masking strategy to provide hard-to-align samples, which improves the alignment performance. Meanwhile, we introduce an explicit uniformity regularizer to ensure the uniformity of the learned representations. Experimental results on benchmark datasets demonstrate the superiority of our model over existing state-of-the-art methods. The code is available at: https://github.com/AzureLeon1/AUG-MAE.

For agents

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

get_harvested_code_for_paper("2402.07225")
get_code_for_paper("2402.07225")
have("2402.07225")

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

curl https://syntology.ai/api/ran/2402.07225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.07225.svg)](https://syntology.ai/paper/2402.07225)

Connect an agent — have() is free.