Papers › D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion

D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion

30 Oct 2023arXiv:2310.19321archive 2025-07-28

Jialin Chen, Shirley Wu, Abhijit Gupta, Rex Ying

The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning. The objective of GNN explainability is to discern the underlying graph structures that have the most significant impact on model predictions. Ensuring that explanations generated are reliable necessitates consideration of the in-distribution property, particularly due to the vulnerability of GNNs to out-of-distribution data. Unfortunately, prevailing explainability methods tend to constrain the generated explanations to the structure of the original graph, thereby downplaying the significance of the in-distribution property and resulting in explanations that lack reliability. To address these challenges, we propose D4Explainer, a novel approach that provides in-distribution GNN explanations for both counterfactual and model-level explanation scenarios. The proposed D4Explainer incorporates generative graph distribution learning into the optimization objective, which accomplishes two goals: 1) generate a collection of diverse counterfactual graphs that conform to the in-distribution property for a given instance, and 2) identify the most discriminative graph patterns that contribute to a specific class prediction, thus serving as model-level explanations. It is worth mentioning that D4Explainer is the first unified framework that combines both counterfactual and model-level explanations. Empirical evaluations conducted on synthetic and real-world datasets provide compelling evidence of the state-of-the-art performance achieved by D4Explainer in terms of explanation accuracy, faithfulness, diversity, and robustness.

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 21 code samples harvested from 1 repository linked to this paper: 15 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 15 ran (5 with no instrument failure; 10 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

graph-and-geometric-learning/d4explainer officialmentioned in paperpytorchSyntology: 21 samples, 15 ran (10 instrument-failed) · 6 unverified report
realmoana/proxyexplainer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Parameterized Explainer for Graph Neural Network (arXiv:2011.04573; that paper's own run record: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 3 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 15 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 6 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.

2ran · honoured contract
7ran · our draft was wrong
3ran; the contract check could not run
3ran
6unverified

Licence: 0 of the 21 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 graph-and-geometric-learning/d4explainer. “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 1 sample 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.

graph-and-geometric-learning/d4explainer official repository 21 samples, 15 ran (10 instrument-failed) · 6 unverified
FeatureExtractor in 24 papers explainers/diff_explainer.py ran · metamorphic tier: deterministic MIT (permissive) · 876af85f8e3ffb2b · report fixture: returned FeatureExtractor · level recorded 2026-09-22
Powerful explainers/diff_explainer.py ran · metamorphic tier: deterministic MIT (permissive) · 224789a60fc208a5 · report fixture: returned Powerful · level recorded 2026-09-22
PowerfulLayer explainers/diff_explainer.py ran · metamorphic tier: deterministic MIT (permissive) · 55f7243fa5953c0d · report fixture: returned PowerfulLayer · level recorded 2026-09-22
discretenoise_single explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · 6dfdb2f6de8a0f00 · report fixture: signature train_adj_b:Tensor/3/float, node_flags:Tensor/2/float, sigma:float/0/float, device:str/0/str · returned tuple · level recorded 2026-09-22
gen_full explainers/diff_explainer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · a4424d0337fb23aa · report fixture: signature batch:Tensor/1/int, mask:Tensor/3/int · returned Tensor · level recorded 2026-09-22
gen_list_of_data_single explainers/diff_explainer.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 2c0b5b94f76fedb0 · report fixture: signature train_x_b:Tensor/3/float, train_adj_b:Tensor/3/float, train_node_flag_b:Tensor/2/float, sigma_list:list/1/float, args:Args/0/? · returned tuple · level recorded 2026-09-22
generate_mask in 24 papers explainers/diff_explainer.py ran · honoured contract fingerprinted MIT (permissive) · d59e27b5fae8a2be · report fixture: signature node_flags:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gnn_pred explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · c450ff9a010d27ad · report fixture: signature graph_batch:MockGraph/0/?, graph_batch_sub:MockGraph/0/?, gnn_model:callable/0/?, ds:MockDataset/0/?, task:str/0/str · returned tuple · level recorded 2026-09-22
graph2tensor explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · bad5406d867eff25 · report fixture: signature graph:callable/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
loss_cf_exp explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · 6a78eeb85c913ca8 · report fixture: signature gnn_model:callable/0/?, graph_batch:GraphBatch/0/?, score:list/1/Tensor, y_pred:Tensor/1/int, y_exp:Tensor/1/int, full_edge:Tensor/2/int, mask:Tensor/2/float, ds:NoneType/0/?, task:str/0/str · returned tuple · level recorded 2026-09-22
loss_func_bce explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · 63fed087bd0312f9 · report fixture: signature score_list:Tensor/3/float, groundtruth:Tensor/3/float, sigma_list:list/1/float, mask:Tensor/3/float, device:device/0/?, sparsity_level:float/0/float · returned Tensor · level recorded 2026-09-22
mask_adjs explainers/diff_explainer.py ran · honoured contract fingerprinted MIT (permissive) · fdd19f4eeaaf2335 · report fixture: signature adjs:Tensor/3/float, node_flags:Tensor/2/float · returned Tensor · level recorded 2026-09-22
masked_instance_norm2D explainers/diff_explainer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · e0e84c89f30caaad · report fixture: signature x:Tensor/4/float, mask:Tensor/4/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
sparsity in 14 papers explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · 270d02a1f79ddaf1 · report fixture: signature score:list/1/Tensor, groundtruth:Tensor/3/float, mask:Tensor/3/float, threshold:float/0/float · returned Tensor · level recorded 2026-09-22
tensor2graph explainers/diff_explainer.py ran · our draft was wrong MIT (permissive) · c88f152103fd6b98 · report fixture: signature graph_batch:callable/0/?, score:list/1/Tensor, mask_adj:Tensor/3/int, threshold:float/0/float · returned Data · level recorded 2026-09-22
DiffExplainer explainers/diff_explainer.py unverified MIT (permissive) · c14f6a99b3a0f100 · report
Explainer in 9 papers explainers/diff_explainer.py unverified MIT (permissive) · 4e59a98458bb3be0 · report
e_map_mutag explainers/diff_explainer.py unverified MIT (permissive) · 910c9cb3a669f5b0 · report
graph_to_mol explainers/diff_explainer.py unverified MIT (permissive) · ffae4597c717f872 · report
model_save explainers/diff_explainer.py unverified MIT (permissive) · 52dde03888435cc5 · report
x_map_mutag explainers/diff_explainer.py unverified MIT (permissive) · 8e3e1e254a4e2c8a · 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 D4Explainer (graph method: D4Explainer). 21 bricks; individually on a fixture: 15 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. DiffExplainer entry · level 0 · unverified · c14f6a99b3a0f100
  2. Explainer helper · level 0 · unverified · 4e59a98458bb3be0
  3. Powerful model · level 1 · ran · 224789a60fc208a5
  4. gen_full helper · level 1 · ran; the contract check could not run (RAISES) · a4424d0337fb23aa
  5. gen_list_of_data_single data_transform · level 1 · ran; the contract check could not run (RAISES) · 2c0b5b94f76fedb0
  6. generate_mask helper · level 1 · ran · honoured contract · d59e27b5fae8a2be
  7. gnn_pred helper · level 1 · ran · our draft was wrong · c450ff9a010d27ad
  8. graph2tensor data_transform · level 1 · ran · our draft was wrong · bad5406d867eff25
  9. loss_cf_exp loss · level 1 · ran · our draft was wrong · 6a78eeb85c913ca8
  10. loss_func_bce loss · level 1 · ran · our draft was wrong · 63fed087bd0312f9
  11. model_save helper · level 0 · unverified · 52dde03888435cc5
  12. sparsity metric · level 1 · ran · our draft was wrong · 270d02a1f79ddaf1
  13. tensor2graph data_transform · level 1 · ran · our draft was wrong · c88f152103fd6b98
  14. graph_to_mol helper · level 0 · unverified · ffae4597c717f872
  15. FeatureExtractor helper · level 1 · ran · 876af85f8e3ffb2b
  16. PowerfulLayer helper · level 1 · ran · 55f7243fa5953c0d
  17. masked_instance_norm2D helper · level 1 · ran; the contract check could not run (RAISES) · e0e84c89f30caaad
  18. discretenoise_single sampler · level 1 · ran · our draft was wrong · 6dfdb2f6de8a0f00
  19. e_map_mutag helper · level 0 · unverified · 910c9cb3a669f5b0
  20. x_map_mutag helper · level 0 · unverified · 8e3e1e254a4e2c8a
  21. mask_adjs helper · level 1 · ran · honoured contract · fdd19f4eeaaf2335

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="2310.19321") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingGraph Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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