Papers › Training Robust Graph Neural Networks by Modeling Noise Dependencies

Training Robust Graph Neural Networks by Modeling Noise Dependencies

27 Feb 2025arXiv:2502.19670archive 2025-07-28

Yeonjun In, Kanghoon Yoon, Sukwon Yun, Kibum Kim, Sungchul Kim, Chanyoung Park

In real-world applications, node features in graphs often contain noise from various sources, leading to significant performance degradation in GNNs. Although several methods have been developed to enhance robustness, they rely on the unrealistic assumption that noise in node features is independent of the graph structure and node labels, thereby limiting their applicability. To this end, we introduce a more realistic noise scenario, dependency-aware noise on graphs (DANG), where noise in node features create a chain of noise dependencies that propagates to the graph structure and node labels. We propose a novel robust GNN, DA-GNN, which captures the causal relationships among variables in the data generating process (DGP) of DANG using variational inference. In addition, we present new benchmark datasets that simulate DANG in real-world applications, enabling more practical research on robust GNNs. Extensive experiments demonstrate that DA-GNN consistently outperforms existing baselines across various noise scenarios, including both DANG and conventional noise models commonly considered in this field.

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 23 code samples: 21 from 2 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 23: 13 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); found in paper text by Syntology: 18 samples from 1 repository, 8 ran (3 with no instrument failure; 5 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 13 samples that ran have no recorded date.

yeonjun-in/torch-DA-GNN officialpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 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

23 samples harvested: 13 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 10 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
1ran · violated contract
8ran · our draft was wrong
2ran
10unverified

Licence: 23 of the 23 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. 2 samples are listed last, in a group without a repository. “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.

yeonjun-in/torch-DA-GNN official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
models/dagnn.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 525e1e3c0743b179 · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded, date not recorded
kl_loss_compute models/dagnn.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 09903567b0509852 · report fixture: signature pred:Tensor/2/float, soft_targets:Tensor/2/float, reduce:bool/0/bool, tempature:int/0/int · returned Tensor · level recorded, date not recorded
sparse_mx_to_torch_sparse_tensor in 41 papers models/dagnn.py ran · our draft was wrong no licence file found · pointer only · f18d89df1cb06ebb · report fixture: signature sparse_mx:coo_matrix/2/float · returned Tensor · level recorded, date not recorded
WtaoZhao/GraphGLOW found in paper text by Syntology 18 samples, 8 ran (5 instrument-failed) · 10 unverified
GraphClf src/core/model_handler.py ran fingerprinted no licence file found · pointer only · e59eb84b321d0d94 · report fixture: returned GraphClf · level recorded 2026-09-22
PivotGCN src/core/model_handler.py ran fingerprinted no licence file found · pointer only · 34e6ee8f6a749d18 · report fixture: returned PivotGCN · level recorded 2026-09-22
SquaredFrobeniusNorm src/core/model_handler.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4e393b15daa9461c · report fixture: signature X:Tensor/3/float · returned Tensor · level recorded 2026-09-22
graph_add_connections src/core/model_handler.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 2959d7d1f9d97761 · report fixture: signature prob_add:float/0/float, seed:int/0/int, adj:ndarray/2/float, enforce_connected:bool/0/bool · returned ndarray · level recorded 2026-09-22
graph_delete_connections src/core/model_handler.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 003e9c87c0f806c8 · report fixture: signature prob_del:float/0/float, seed:int/0/int, adj:ndarray/2/float, enforce_connected:bool/0/bool · returned ndarray · level recorded 2026-09-22
normalize_dense_feature src/core/model_handler.py ran · violated contract fingerprinted no licence file found · pointer only · 8e2d946a9f148d1c · report fixture: signature mx:ndarray/2/float · returned ndarray · level recorded 2026-09-22
normalize_features in 20 papers src/core/model_handler.py ran · our draft was wrong no licence file found · pointer only · 39cba20da9f36113 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
sample_pivots src/core/model_handler.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 37d7eaf77cc50f2c · report fixture: signature node_vec:Tensor/2/float, s:int/0/int · returned tuple · level recorded 2026-09-22
Model in 227 papers src/core/model_handler.py unverified no licence file found · pointer only · acf8a11b99d878de · report
ModelHandler src/core/model_handler.py unverified no licence file found · pointer only · 53e9ee6400b40544 · report
PivotGCNLayer src/core/model_handler.py unverified no licence file found · pointer only · ff9b4e3fa96e5336 · report
compute_pivot_adj src/core/model_handler.py unverified no licence file found · pointer only · 604480989d4bef59 · report
diff in 16 papers src/core/model_handler.py unverified no licence file found · pointer only · 29922ecc7c935e89 · report
distribute src/core/model_handler.py unverified no licence file found · pointer only · 4973e8248c7263d5 · report
get_prob in 6 papers src/core/model_handler.py unverified no licence file found · pointer only · 0bc86955f61ae146 · report
load_data in 700 papers src/core/model_handler.py unverified no licence file found · pointer only · 5bb7213aec5d4456 · report
load_fb100 in 12 papers src/core/model_handler.py unverified no licence file found · pointer only · fdfd9288adf2c45d · report
prepare_datasets in 13 papers src/core/model_handler.py unverified no licence file found · pointer only · b450d45f806dd32a · report
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located ran · honoured contract licence of this copy not recorded · 4cf9dcdd60711db4 · report fixture: signature labels:Tensor/1/int, output:Tensor/2/float · returned float · level recorded 2026-09-22
parse_index_file in 54 papers repository not located ran · honoured contract licence of this copy not recorded · c1d6392f89c5e495 · report fixture: signature filename:str/0/str · returned list · level recorded, date not recorded

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 DA-GNN (graph method: DA-GNN). 20 bricks; individually on a fixture: 10 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. ModelHandler entry · level 0 · unverified · 53e9ee6400b40544
  2. Model helper · level 0 · unverified · acf8a11b99d878de
  3. SquaredFrobeniusNorm loss · level 1 · ran · our draft was wrong · 4e393b15daa9461c
  4. compute_pivot_adj helper · level 0 · unverified · 604480989d4bef59
  5. diff loss · level 0 · unverified · 29922ecc7c935e89
  6. distribute helper · level 0 · unverified · 4973e8248c7263d5
  7. get_prob loss · level 0 · unverified · 0bc86955f61ae146
  8. prepare_datasets helper · level 0 · unverified · b450d45f806dd32a
  9. sample_pivots helper · level 1 · ran · our draft was wrong · 37d7eaf77cc50f2c
  10. GraphClf helper · level 1 · ran · e59eb84b321d0d94
  11. accuracy helper · level 1 · ran · honoured contract · 4cf9dcdd60711db4
  12. load_data helper · level 0 · unverified · 5bb7213aec5d4456
  13. PivotGCN helper · level 1 · ran · 34e6ee8f6a749d18
  14. graph_add_connections helper · level 1 · ran · our draft was wrong · 2959d7d1f9d97761
  15. graph_delete_connections helper · level 1 · ran · our draft was wrong · 003e9c87c0f806c8
  16. load_fb100 helper · level 0 · unverified · fdfd9288adf2c45d
  17. normalize_dense_feature helper · level 1 · ran · violated contract · 8e2d946a9f148d1c
  18. normalize_features helper · level 1 · ran · our draft was wrong · 39cba20da9f36113
  19. parse_index_file helper · level 1 · ran · honoured contract · c1d6392f89c5e495
  20. PivotGCNLayer helper · level 0 · unverified · ff9b4e3fa96e5336

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="2502.19670") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Variational Inference

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