Papers › Graph Edit Distance with General Costs Using Neural Set Divergence

Graph Edit Distance with General Costs Using Neural Set Divergence

26 Sep 2024arXiv:2409.17687archive 2025-07-28

Eeshaan Jain, Indradyumna Roy, Saswat Meher, Soumen Chakrabarti, Abir De

Graph Edit Distance (GED) measures the (dis-)similarity between two given graphs, in terms of the minimum-cost edit sequence that transforms one graph to the other. However, the exact computation of GED is NP-Hard, which has recently motivated the design of neural methods for GED estimation. However, they do not explicitly account for edit operations with different costs. In response, we propose GRAPHEDX, a neural GED estimator that can work with general costs specified for the four edit operations, viz., edge deletion, edge addition, node deletion and node addition. We first present GED as a quadratic assignment problem (QAP) that incorporates these four costs. Then, we represent each graph as a set of node and edge embeddings and use them to design a family of neural set divergence surrogates. We replace the QAP terms corresponding to each operation with their surrogates. Computing such neural set divergence require aligning nodes and edges of the two graphs. We learn these alignments using a Gumbel-Sinkhorn permutation generator, additionally ensuring that the node and edge alignments are consistent with each other. Moreover, these alignments are cognizant of both the presence and absence of edges between node-pairs. Experiments on several datasets, under a variety of edit cost settings, show that GRAPHEDX consistently outperforms state-of-the-art methods and heuristics in terms of prediction error.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 15 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 20 ran (5 with no instrument failure; 15 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

structlearning/graphedx officialmentioned in papermentioned on GitHubpytorchMITSyntology: 25 samples, 20 ran (15 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

25 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 15 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran · our draft was wrong
2ran; the contract check could not run
5ran
5unverified

Licence: 8 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from structlearning/graphedx. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

structlearning/graphedx official repository 25 samples, 20 ran (15 instrument-failed) · 5 unverified
approximate_hamming_similarity GMN/loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 95afc6f0962b5c2a · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
asymm_embed_mat_l1_dist models/graphedx.py ran · our draft was wrong fingerprinted MIT (permissive) · 8ad55980e1c03523 · report fixture: signature query_features:Tensor/3/float, corpus_features:Tensor/3/float, transport_plan:Tensor/3/float, add_cost:float/0/float, del_cost:float/0/float · returned Tensor · level recorded 2026-09-22
compute_loss in 97 papers
census: 11 implementations from 11 papers, 9 distinct outputs across 7 buckets, one shared input per bucket this sample: bucket 2 of 7, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
models/graphedx.py ran · our draft was wrong fingerprinted MIT (permissive) · 310b4b2e126ed8b6 · report fixture: signature lower_bound:Tensor/2/float, upper_bound:Tensor/2/float, out:Tensor/2/float · returned Tensor · level recorded 2026-09-22
euclidean_distance in 29 papers GMN/loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 69e7dcdc10127913 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
evaluate in 514 papers src/train_graphedx.py ran MIT (permissive) · 0ab108ac04cb5ade · report fixture: signature model:callable/0/?, sampler:SimpleSampler/0/? · returned tuple · level recorded 2026-09-24
evaluate in 514 papers src/train_graphedx_label.py ran MIT (permissive) · 18a32d300eb754e3 · report fixture: signature model:callable/0/?, sampler:SimpleSampler/0/? · returned tuple · level recorded 2026-09-24
get_default_gmn_config utils/model_utils.py ran · our draft was wrong MIT (permissive) · b184bb466ed11cbe · report fixture: signature conf:MinimalConfig/0/? · returned dict · level recorded 2026-09-24
get_graph_features models/graphedx.py ran · our draft was wrong MIT (permissive) · 9369db470a2582dd · report fixture: signature graphs:GraphBatch/0/? · returned tuple · level recorded 2026-09-22
graph_prop_once models/graphedx.py ran; the contract check could not run (RAISES) MIT (permissive) · 2a761f476bdc2e9c · report fixture: signature node_states:Tensor/2/float, from_idx:Tensor/1/int, to_idx:Tensor/1/int, message_net:callable/0/?, aggregation_module:callable/0/?, edge_features:Tensor/2/float · returned Tensor · level recorded 2026-09-24
modify_gmn_main_config utils/model_utils.py ran MIT (permissive) · 0127ae44341328ed · report fixture: signature gmn_config:dict/0/?, conf:Conf/0/?, logger:Logger/0/? · returned dict · level recorded 2026-09-24
modify_gmn_main_config_shallow utils/model_utils.py ran MIT (permissive) · 5eabd9835e8a4d18 · report fixture: signature gmn_config:dict/0/?, conf:Conf/0/?, logger:Logger/0/? · returned dict · level recorded 2026-09-24
pairwise_dot_product_similarity GMN/fast_graphmatchingnetwork.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9a12e8146ffaef47 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
pairwise_loss in 6 papers GMN/loss.py ran MIT (permissive) here; the stored copy is pointer only · a4f527c188a5f7fd · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, labels:Tensor/1/int, loss_type:str/0/str, margin:float/0/float · returned Tensor · level recorded 2026-09-25
permute_graph_nodes GMN/dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ff70e907d342b902 · report fixture: signature g:Graph/0/? · returned Graph · level recorded 2026-09-25
pytorch_sample_gumbel models/graphedx.py ran · our draft was wrong MIT (permissive) · b0cbba82a28e65dd · report fixture: signature shape:tuple/1/int, device:str/0/str, eps:float/0/float · returned Tensor · level recorded 2026-09-22
pytorch_sinkhorn_iters models/graphedx.py ran; the contract check could not run (RAISES) MIT (permissive) · 0f4c11f88b918a82 · report fixture: signature log_alpha:Tensor/3/float, device:str/0/str, temperature:float/0/float, noise_factor:float/0/float, num_iters:int/0/int · returned Tensor · level recorded 2026-09-22
split_and_stack models/graphedx.py ran · our draft was wrong MIT (permissive) · 065225e446072baa · report fixture: signature features:Tensor/2/float, graph_sizes:list/1/int, max_set_size:int/0/int · returned tuple · level recorded 2026-09-22
split_to_query_and_corpus models/graphedx.py ran · our draft was wrong MIT (permissive) · 2468f115a7f89d3a · report fixture: signature features:Tensor/2/float, graph_sizes:list/1/int · returned tuple · level recorded 2026-09-22
substitute_random_edges GMN/dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 19a40503f8bc9732 · report fixture: signature g:Graph/0/?, n:int/0/int · returned Graph · level recorded 2026-09-25
unsorted_segment_sum in 33 papers models/graphedx.py ran · our draft was wrong MIT (permissive) · 65ea513617120aff · report fixture: signature data:Tensor/2/float, segment_ids:Tensor/1/int, num_segments:int/0/int · returned Tensor · level recorded 2026-09-22
GRAPHEDX_no_xor models/graphedx.py unverified MIT (permissive) · b249ba548c0c9be1 · report
GraphEncoder in 9 papers models/graphedx.py unverified MIT (permissive) · 3f351498dcb392cc · report
GraphPropLayer models/graphedx.py unverified MIT (permissive) · 303a3b8ce9e8fc66 · report
pairwise_cosine_similarity in 5 papers GMN/fast_graphmatchingnetwork.py unverified MIT (permissive) here; the stored copy is pointer only · b0a1692650a31872 · report
pairwise_euclidean_similarity GMN/fast_graphmatchingnetwork.py unverified MIT (permissive) here; the stored copy is pointer only · 95b1b93041fc8ad0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for GRAPHEDX (graph method: GRAPHEDX). 12 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. GRAPHEDX_no_xor entry · level 0 · unverified · b249ba548c0c9be1
  2. GraphEncoder helper · level 0 · unverified · 3f351498dcb392cc
  3. GraphPropLayer helper · level 0 · unverified · 303a3b8ce9e8fc66
  4. asymm_embed_mat_l1_dist helper · level 1 · ran · our draft was wrong · 8ad55980e1c03523
  5. compute_loss helper · level 1 · ran · our draft was wrong · 310b4b2e126ed8b6
  6. get_graph_features helper · level 1 · ran · our draft was wrong · 9369db470a2582dd
  7. pytorch_sinkhorn_iters helper · level 1 · ran; the contract check could not run (RAISES) · 0f4c11f88b918a82
  8. split_and_stack helper · level 1 · ran · our draft was wrong · 065225e446072baa
  9. graph_prop_once helper · level 1 · ran; the contract check could not run (RAISES) · 2a761f476bdc2e9c
  10. pytorch_sample_gumbel helper · level 1 · ran · our draft was wrong · b0cbba82a28e65dd
  11. split_to_query_and_corpus helper · level 1 · ran · our draft was wrong · 2468f115a7f89d3a
  12. unsorted_segment_sum helper · level 1 · ran · our draft was wrong · 65ea513617120aff

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2409.17687") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections