SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.14929 · NeurIPS · 2022

Efficient Graph Similarity Computation with Alignment Regularization

Wei Zhuo, Guang Tan

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 4 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/2406.14929.json · badge: /api/ran/2406.14929.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
JhuoW/ERIC canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
jhuow/eric canonical (classifier label)
classifier basis: classifier_2025
4 ran · 3 no recorded run
FunctionStatusWhere it lives
FF Ran
ran on a synthesized input · constructed an object; no result was computed
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("2b3ca014811aa550")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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.

MLPLayers Ran
ran on a synthesized input · constructed an object; no result was computed
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("9b47dc2703adb259")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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.

TensorNetworkModule Ran
ran on a synthesized input · constructed an object; no result was computed
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("63091473be7df98b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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.

gen_pairs Ran
ran; our contract draft was wrong, not the code
JhuoW/ERIC/DataHelper/data_utils.py
pointer only (licence: NONE) · get_code("d27e95dc93971430")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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_positive_expectation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("677840a48213de47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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_positive_expectation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JhuoW/ERIC/utils/gan_losses.py
pointer only (licence: NONE) · get_code("565c2a174cca323f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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_pred_result Ran
ran, honoured the contract we drafted
JhuoW/ERIC/exp/exp.py
pointer only (licence: NONE) · get_code("5260f26ac027fe21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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_true_result Ran
ran, honoured the contract we drafted
JhuoW/ERIC/exp/exp.py
pointer only (licence: NONE) · get_code("c65d2cd8f05a8c39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

iterate_get_graphs Ran
ran; our contract draft was wrong, not the code
JhuoW/ERIC/DataHelper/simgnn_utils.py
pointer only (licence: NONE) · get_code("dc317f1dcd7db3e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

normalized_exp_kernel_ged Ran
ran, honoured the contract we drafted
JhuoW/ERIC/DataHelper/simgnn_utils.py
pointer only (licence: NONE) · get_code("9a35c06670c35daa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

sorted_nicely Ran
ran; our contract draft was wrong, not the code
JhuoW/ERIC/DataHelper/simgnn_utils.py
pointer only (licence: NONE) · get_code("5f1abfd2b5c44a6a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

to_directed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JhuoW/ERIC/DataHelper/data_utils.py
pointer only (licence: NONE) · get_code("a2dd27adcf74cf43")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

GCL Not yet run
unverified (harvested, no recorded run)
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("a8eb12ddd98b0279")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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.

GSC Not yet run
unverified (harvested, no recorded run)
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("5a699d84c35acfc9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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.

gen_pair Not yet run
unverified (harvested, no recorded run)
JhuoW/ERIC/DataHelper/data_utils.py
pointer only (licence: NONE) · get_code("289900c751839228")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/ERIC 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.

raise_measure_error Not yet run
unverified (harvested, no recorded run)
jhuow/eric/model/GSC.py
pointer only (licence: NONE) · get_code("31f0f7b2c907786e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jhuow/eric 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 11 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
get_positive_expectation
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2402.16302 (2024-02)
Graph Diffusion Policy Optimization
iterate_get_graphs 1 other paper
1 dated earlier
2007.04395 (2020-07)
Multilevel Graph Matching Networks for Deep Graph Similarity Learning
normalized_exp_kernel_ged 1 other paper
1 dated earlier
2007.04395 (2020-07)
Multilevel Graph Matching Networks for Deep Graph Similarity Learning
sorted_nicely 1 other paper
1 dated earlier
2007.04395 (2020-07)
Multilevel Graph Matching Networks for Deep Graph Similarity Learning

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

We consider the graph similarity computation (GSC) task based on graph edit distance (GED) estimation. State-of-the-art methods treat GSC as a learningbased prediction task using Graph Neural Networks (GNNs). To capture finegrained interactions between pair-wise graphs, these methods mostly contain a node-level matching module in the end-to-end learning pipeline, which causes high computational costs in both the training and inference stages. We show that the expensive node-to-node matching module is not necessary for GSC, and highquality learning can be attained with a simple yet powerful regularization technique, which we call the Alignment Regularization (AReg). In the training stage, the AReg term imposes a node-graph correspondence constraint on the GNN encoder. In the inference stage, the graph-level representations learned by the GNN encoder are directly used to compute the similarity score without using AReg again to speed up inference. We further propose a multi-scale GED discriminator to enhance the expressive ability of the learned representations. Extensive experiments on real-world datasets demonstrate the effectiveness, efficiency and transferability of our approach.

For agents

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

get_harvested_code_for_paper("2406.14929")
get_code_for_paper("2406.14929")
have("2406.14929")

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

curl https://syntology.ai/api/ran/2406.14929.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.14929.svg)](https://syntology.ai/paper/2406.14929)

Connect an agent — have() is free.