Papers › Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

5 Feb 2022arXiv:2202.02514archive 2025-07-28

Jaehyeong Jo, Seul Lee, Sung Ju Hwang

Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or cannot sufficiently model the complex dependency between nodes and edges, which is crucial for generating real-world graphs such as molecules. To overcome such limitations, we propose a novel score-based generative model for graphs with a continuous-time framework. Specifically, we propose a new graph diffusion process that models the joint distribution of the nodes and edges through a system of stochastic differential equations (SDEs). Then, we derive novel score matching objectives tailored for the proposed diffusion process to estimate the gradient of the joint log-density with respect to each component, and introduce a new solver for the system of SDEs to efficiently sample from the reverse diffusion process. We validate our graph generation method on diverse datasets, on which it either achieves significantly superior or competitive performance to the baselines. Further analysis shows that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule, demonstrating the effectiveness of the system of SDEs in modeling the node-edge relationships. Our code is available at https://github.com/harryjo97/GDSS.

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.

Syntology holds a reference implementation of score-based generative model for graphs, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='score-based generative model for graphs') (how to connect); the free check have('2202.02514') needs no token.

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

Code

Syntology 26 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

harryjo97/gdss officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 6 ran (3 instrument-failed) · 7 unverified report
AdrienC21/CCSD mentioned on GitHubpytorchSyntology: 13 samples, 8 ran (4 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

26 samples harvested: 14 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
7ran · our draft was wrong
4ran
12unverified

Licence: 13 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

harryjo97/gdss official repository 13 samples, 6 ran (3 instrument-failed) · 7 unverified
DenseGCNConv models/ScoreNetwork_A.py ran no licence file found · pointer only · 5a02983f323406e0 · report fixture: signature x:Tensor/3/float, adj:Tensor/3/float, mask:NoneType/0/?, add_loop:bool/0/bool · returned Tensor · level recorded 2026-09-24
MLP in 375 papers models/ScoreNetwork_A.py ran no licence file found · pointer only · 040c0c8297f0b85e · report fixture: returned MLP · level recorded 2026-09-22
mask_adjs models/ScoreNetwork_A.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 48beee2482c52c79 · report fixture: signature adjs:Tensor/3/float, flags:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mask_x models/ScoreNetwork_A.py ran · honoured contract fingerprinted no licence file found · pointer only · 9e2571123018843f · report fixture: signature x:Tensor/3/float, flags:Tensor/2/float · returned Tensor · level recorded 2026-09-22
node_feature_to_matrix models/ScoreNetwork_A.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0d1b1ea523b61fc1 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
pow_tensor models/ScoreNetwork_A.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f336fdfe65a2d094 · report fixture: signature x:Tensor/3/float, cnum:int/0/int · returned Tensor · level recorded 2026-09-22
AttentionLayer in 30 papers models/ScoreNetwork_A.py unverified no licence file found · pointer only · 4459f5d4f76fdabb · report
BaselineNetwork models/ScoreNetwork_A.py unverified no licence file found · pointer only · 94df2c222ce171b3 · report
BaselineNetworkLayer models/ScoreNetwork_A.py unverified no licence file found · pointer only · 23a353751b044a84 · report
ScoreNetworkA models/ScoreNetwork_A.py unverified no licence file found · pointer only · e4c3555e138cd8e7 · report
glorot in 26 papers models/ScoreNetwork_A.py unverified no licence file found · pointer only · 99fea4b7e50f6464 · report
zeros in 26 papers models/ScoreNetwork_A.py unverified no licence file found · pointer only · ea9c6ff61fbc9c4e · report
AdrienC21/CCSD community (archive-listed) 13 samples, 8 ran (4 instrument-failed) · 5 unverified
DenseGCNConv ccsd/src/models/ScoreNetwork_A.py ran · metamorphic tier: deterministic MIT (permissive) · d2e486d574414d1d · report fixture: returned DenseGCNConv · level recorded 2026-09-22
MLP in 375 papers ccsd/src/models/ScoreNetwork_A.py ran · metamorphic tier: deterministic MIT (permissive) · 63298408c7c090f1 · report fixture: returned MLP · level recorded 2026-09-22
default_mask ccsd/src/models/ScoreNetwork_A.py ran · honoured contract MIT (permissive) · f024485a6f7e3fcd · report fixture: signature n:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
get_ones ccsd/src/models/ScoreNetwork_A.py ran · our draft was wrong MIT (permissive) · 748e4359ea4a572a · report fixture: signature shape:tuple/1/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
get_ones_cache ccsd/src/models/ScoreNetwork_A.py ran · our draft was wrong MIT (permissive) · ad6a260e14f905b6 · report fixture: signature shape:tuple/1/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
mask_adjs ccsd/src/models/ScoreNetwork_A.py ran · our draft was wrong MIT (permissive) · accdc25084458694 · report fixture: signature adjs:Tensor/3/float, flags:NoneType/0/? · returned Tensor · level recorded 2026-09-22
mask_x ccsd/src/models/ScoreNetwork_A.py ran · honoured contract fingerprinted MIT (permissive) · 6ab53333836fe2fd · report fixture: signature x:Tensor/3/float, flags:Tensor/2/float · returned Tensor · level recorded 2026-09-22
pow_tensor ccsd/src/models/ScoreNetwork_A.py ran · our draft was wrong fingerprinted MIT (permissive) · 4950af49e1d0760a · report fixture: signature x:Tensor/3/float, cnum:int/0/int · returned Tensor · level recorded 2026-09-22
AttentionLayer in 30 papers ccsd/src/models/ScoreNetwork_A.py unverified MIT (permissive) · e3d26a1b52a8e0cd · report
ScoreNetworkA ccsd/src/models/ScoreNetwork_A.py unverified MIT (permissive) · f778f8f279b1775e · report
glorot in 26 papers ccsd/src/models/ScoreNetwork_A.py unverified MIT (permissive) · b26ee0603cfc49f5 · report
zeros in 26 papers ccsd/src/models/ScoreNetwork_A.py unverified MIT (permissive) · 5f1a4e1cb60dea51 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for score-based generative model for graphs (graph method: score-based generative model for graphs), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. symmetric_splitting_step entry · level 2 · ran · fc298ad2db6cfee4bc38603b2260285148c873350337f5c765c5993d33a705ce

2 sibling assemblies for score-based generative model for graphs (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for score-based generative model for graphs (graph method: score-based generative model for graphs). 13 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ScoreNetworkA entry · level 0 · unverified · f778f8f279b1775e
  2. AttentionLayer helper · level 0 · unverified · e3d26a1b52a8e0cd
  3. MLP helper · level 1 · ran · 63298408c7c090f1
  4. default_mask helper · level 1 · ran · honoured contract · f024485a6f7e3fcd
  5. mask_adjs helper · level 1 · ran · our draft was wrong · accdc25084458694
  6. pow_tensor helper · level 1 · ran · our draft was wrong · 4950af49e1d0760a
  7. Attention helper · level 0 · unverified · 7b774bdd34c82a39
  8. mask_x helper · level 1 · ran · honoured contract · 6ab53333836fe2fd
  9. glorot helper · level 0 · unverified · b26ee0603cfc49f5
  10. zeros helper · level 0 · unverified · 5f1a4e1cb60dea51
  11. get_ones helper · level 1 · ran · our draft was wrong · 748e4359ea4a572a
  12. DenseGCNConv helper · level 1 · ran · d2e486d574414d1d
  13. get_ones_cache helper · level 1 · ran · our draft was wrong · ad6a260e14f905b6

harvested Assembly for score-based generative model for graphs (graph method: score-based generative model for graphs). 13 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ScoreNetworkA entry · level 0 · unverified · e4c3555e138cd8e7
  2. AttentionLayer helper · level 0 · unverified · 4459f5d4f76fdabb
  3. BaselineNetwork helper · level 0 · unverified · 94df2c222ce171b3
  4. MLP helper · level 1 · ran · 040c0c8297f0b85e
  5. mask_adjs helper · level 1 · ran · our draft was wrong · 48beee2482c52c79
  6. pow_tensor helper · level 1 · ran · our draft was wrong · f336fdfe65a2d094
  7. Attention helper · level 0 · unverified · 33bc3c99206d9a3e
  8. mask_x helper · level 1 · ran · honoured contract · 9e2571123018843f
  9. BaselineNetworkLayer helper · level 0 · unverified · 23a353751b044a84
  10. DenseGCNConv helper · level 1 · ran · 5a02983f323406e0
  11. node_feature_to_matrix helper · level 1 · ran · our draft was wrong · 0d1b1ea523b61fc1
  12. glorot helper · level 0 · unverified · 99fea4b7e50f6464
  13. zeros helper · level 0 · unverified · ea9c6ff61fbc9c4e

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="2202.02514") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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