SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.22897 · ICLR · 2025

Charting the Design Space of Neural Graph Representations for Subgraph Matching

Abir De, Soumen Chakrabarti, Indradyumna Roy, Vaibhav Raj, Ashwin Ramachandran

arXiv · PDF · Open in the Atlas

Code that ran

12 of 18 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 0 have no contract verdict; 12 failures of our instrument; 6 no recorded run), measured 2026-11-22; 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/2510.22897.json · badge: /api/ran/2510.22897.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
structlearning/neural-subm-design-space canonical (classifier label)
classifier basis: census
12 ran · 6 no recorded run
FunctionStatusWhere it lives
approximate_hamming_similarity Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/loss.py
pointer only (licence: NONE) · get_code("95afc6f0962b5c2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

euclidean_distance Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/loss.py
pointer only (licence: NONE) · get_code("69e7dcdc10127913")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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_graph_features Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/utils/model_utils.py
pointer only (licence: NONE) · get_code("9369db470a2582dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

pairwise_dot_product_similarity Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/graphmatchingnetwork.py
pointer only (licence: NONE) · get_code("9a12e8146ffaef47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

pairwise_loss Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/loss.py
pointer only (licence: NONE) · get_code("a4f527c188a5f7fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

permute_graph_nodes Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/dataset.py
pointer only (licence: NONE) · get_code("ff70e907d342b902")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

reshape_and_split_tensor Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/utils.py
pointer only (licence: NONE) · get_code("0682e111e0999ca2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

sample_gumbel Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/utils/model_utils.py
pointer only (licence: NONE) · get_code("1deb3935695bf27e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

segment_sum Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
structlearning/neural-subm-design-space/GMN/segment.py
pointer only (licence: NONE) · get_code("be8026886bac2429")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

sinkhorn_iters Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
structlearning/neural-subm-design-space/utils/model_utils.py
pointer only (licence: NONE) · get_code("69274fe8fd16ca44")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

substitute_random_edges Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/dataset.py
pointer only (licence: NONE) · get_code("19a40503f8bc9732")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
structlearning/neural-subm-design-space/GMN/segment.py
pointer only (licence: NONE) · get_code("65ea513617120aff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

auc Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/GMN/evaluation.py
pointer only (licence: NONE) · get_code("178cde1547585aa1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

compute_similarity Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/GMN/evaluation.py
pointer only (licence: NONE) · get_code("445104cd8f5adc37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

exact_hamming_similarity Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/GMN/evaluation.py
pointer only (licence: NONE) · get_code("e85d09a07bd37574")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

get_datasets Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/subgraph_matching/dataset.py
pointer only (licence: NONE) · get_code("120db67dbd20f0a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

pairwise_cosine_similarity Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/GMN/graphmatchingnetwork.py
pointer only (licence: NONE) · get_code("b0a1692650a31872")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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.

pairwise_euclidean_similarity Not yet run
unverified (harvested, no recorded run)
structlearning/neural-subm-design-space/GMN/graphmatchingnetwork.py
pointer only (licence: NONE) · get_code("95b1b93041fc8ad0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, structlearning/neural-subm-design-space 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
approximate_hamming_similarity 2 other papers
2 dated earlier
2401.09953 (2024-01)
Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
euclidean_distance 2 other papers
2 dated earlier
2401.09953 (2024-01)
Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
get_graph_features 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
pairwise_cosine_similarity 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
pairwise_dot_product_similarity 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
pairwise_euclidean_similarity 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
pairwise_loss 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
permute_graph_nodes 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
substitute_random_edges 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence
unsorted_segment_sum 1 other paper
1 dated earlier
2409.17687 (2024-09)
Graph Edit Distance with General Costs Using Neural Set Divergence

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

Subgraph matching is vital in knowledge graph (KG) question answering, molecule design, scene graph, code and circuit search, etc. Neural methods have shown promising results for subgraph matching. Our study of recent systems suggests refactoring them into a unified design space for graph matching networks. Existing methods occupy only a few isolated patches in this space, which remains largely uncharted. We undertake the first comprehensive exploration of this space, featuring such axes as attention-based vs. soft permutation-based interaction between query and corpus graphs, aligning nodes vs. edges, and the form of the final scoring network that integrates neural representations of the graphs. Our extensive experiments reveal that judicious and hitherto-unexplored combinations of choices in this space lead to large performance benefits. Beyond better performance, our study uncovers valuable insights and establishes general design principles for neural graph representation and interaction, which may be of wider interest. Our code and datasets are publicly available at https://github.com/structlearning/neural-subm-design-space. * Vaibhav and Indradyumna contributed equally. Ashwin Ramachandran did this work while at IIT Bombay.

For agents

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

get_harvested_code_for_paper("2510.22897")
get_code_for_paper("2510.22897")
have("2510.22897")

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

curl https://syntology.ai/api/ran/2510.22897.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.22897.svg)](https://syntology.ai/paper/2510.22897)

Connect an agent — have() is free.