Papers › Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation

Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation

9 Jul 2024arXiv:2407.11052archive 2025-07-28

Meihan Liu, Zhen Zhang, Jiachen Tang, Jiajun Bu, Bingsheng He, Sheng Zhou

Unsupervised Graph Domain Adaptation (UGDA) involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph under domain discrepancies. Despite the proliferation of methods designed for this emerging task, the lack of standard experimental settings and fair performance comparisons makes it challenging to understand which and when models perform well across different scenarios. To fill this gap, we present the first comprehensive benchmark for unsupervised graph domain adaptation named GDABench, which encompasses 16 algorithms across 5 datasets with 74 adaptation tasks. Through extensive experiments, we observe that the performance of current UGDA models varies significantly across different datasets and adaptation scenarios. Specifically, we recognize that when the source and target graphs face significant distribution shifts, it is imperative to formulate strategies to effectively address and mitigate graph structural shifts. We also find that with appropriate neighbourhood aggregation mechanisms, simple GNN variants can even surpass state-of-the-art UGDA baselines. To facilitate reproducibility, we have developed an easy-to-use library PyGDA for training and evaluating existing UGDA methods, providing a standardized platform in this community. Our source codes and datasets can be found at: https://github.com/pygda-team/pygda.

PaperPDFConference PDFCodeCode Syntology ran

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

The archive's official repository (pygda-team/pygda) was not harvested; the 47 samples below come from 6 repositories the archive does not mark official.

Syntology 47 code samples harvested from 6 repositories linked to this paper: 38 ran (of which 0 constructed an object rather than computing a result; 26 with no instrument failure: 4 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 12 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 47 samples from 6 repositories, 38 ran (26 with no instrument failure; 12 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 2 of its repositories that Syntology harvested for other papers:

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. 4 of the 38 samples that ran have no recorded date.

pygda-team/pygda officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested 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

47 samples harvested: 38 ran (of which 0 constructed an object rather than computing a result; 26 with no instrument failure: 4 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 9 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.

4ran · honoured contract
12ran · our draft was wrong
22ran
9unverified

Licence: 21 of the 47 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 6 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”. “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.

GRAND-Lab/UDAGCN found in paper text by Syntology 1 sample, 0 ran · 1 unverified
ppmi_encode UDAGCN_demo.py unverified MIT (permissive) · c3e540ae5cd25884 · report
Shen-Lab/GDA-SpecReg found in paper text by Syntology 9 samples, 7 ran (1 instrument-failed) · 2 unverified
calculate_gradient_penalty paper_topic_classification/ogbn_arxiv_semisupervised/gnn_specreg.py ran Apache-2.0 (permissive) · 004a0bb7a8a25e40 · report fixture: signature critic:callable/0/?, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
spectral_regularization_smooth paper_topic_classification/ogbn_arxiv_semisupervised/gnn_specreg.py ran Apache-2.0 (permissive) · b5d45277ad341bad · report fixture: signature x:Tensor/2/float, x0:Tensor/2/float, eivec:Tensor/2/float, eival:Tensor/1/float, thres:float/0/float · returned Tensor · level recorded 2026-09-24
test in 377 papers paper_topic_classification/ogbn_arxiv_semisupervised/gnn.py ran · honoured contract Apache-2.0 (permissive) · 8e6629dff4ea0a71 · report fixture: signature model:callable/0/?, data:Data/0/?, split_idx:dict/0/?, evaluator:SimpleEvaluator/0/? · returned tuple · level recorded, date not recorded
test in 377 papers paper_topic_classification/ogbn_arxiv_semisupervised/gnn_da.py ran Apache-2.0 (permissive) · f556b6370898ea98 · report fixture: signature model:callable/0/?, data:DummyData/0/?, split_idx:dict/0/?, evaluator:DummyEvaluator/0/?, critic:callable/0/? · returned tuple · level recorded 2026-09-24
train in 522 papers paper_topic_classification/ogbn_arxiv_unsupervised/gnn.py ran · our draft was wrong Apache-2.0 (permissive) · 82f54a95d4951b19 · report fixture: signature model:callable/0/?, data:Data/0/?, train_idx:Tensor/1/int, optimizer:Adam/0/? · returned float · level recorded, date not recorded
train in 522 papers paper_topic_classification/ogbn_arxiv_semisupervised/gnn.py ran Apache-2.0 (permissive) · 758d5dd9e231d846 · report fixture: signature model:callable/0/?, data:Data/0/?, train_idx:Tensor/1/int, valid_idx:Tensor/1/int, idx_semi:Tensor/1/int, optimizer:Adam/0/? · returned float · level recorded 2026-09-24
train in 522 papers paper_topic_classification/ogbn_arxiv_unsupervised/gnn_da.py ran Apache-2.0 (permissive) · 20a9feb6dd535706 · report fixture: signature model:callable/0/?, data:Data/0/?, train_idx:Tensor/1/int, val_idx:Tensor/1/int, optimizer:Adam/0/?, critic:callable/0/?, optimizer_c:Adam/0/?, gamma:float/0/float · returned tuple · level recorded 2026-09-24
get_laplacian_evd paper_topic_classification/ogbn_arxiv_semisupervised/gnn_specreg.py unverified Apache-2.0 (permissive) · 7a8a7b03eee3a24e · report
train in 522 papers paper_topic_classification/ogbn_arxiv_semisupervised/gnn_da.py unverified Apache-2.0 (permissive) · 0b6755f3ee7c7fde · report
Meihan-Liu/24AAAI-A2GNN found in paper text by Syntology 3 samples, 3 ran (1 instrument-failed) · 0 unverified
MMD in 8 papers A2GNN-adv/utils.py ran no licence file found · pointer only · ca363e4b450c262a · report fixture: signature source_feat:Tensor/2/float, target_feat:Tensor/2/float, sampling_num:int/0/int, times:int/0/int · returned Tensor · level recorded 2026-09-24
evaluate in 514 papers A2GNN-adv/utils.py ran no licence file found · pointer only · fa70e2f6d7d22341 · report fixture: signature data:Data/0/?, model:callable/0/?, conv_time:int/0/int · returned tuple · level recorded 2026-09-24
guassian_kernel in 9 papers A2GNN-adv/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f4a8968b88a150d1 · report fixture: signature source:Tensor/2/float, target:Tensor/2/float, kernel_mul:float/0/float, kernel_num:int/0/int, fix_sigma:NoneType/0/? · returned Tensor · level recorded 2026-09-22
Skyorca/JHGDA found in paper text by Syntology 5 samples, 4 ran (1 instrument-failed) · 1 unverified
generate_core_view utils.py ran · our draft was wrong no licence file found · pointer only · 8150ea33ad187337 · report fixture: signature path:str/0/str, kmax:int/0/int · returned tuple · level recorded 2026-09-24
generate_feture utils.py ran no licence file found · pointer only · 3bcef2af74e17622 · report fixture: signature graph:Graph/0/?, max_degree:int/0/int · returned Tensor · level recorded 2026-09-24
generate_label in 8 papers utils.py ran no licence file found · pointer only · d6c8e0fb0c0f0440 · report fixture: signature path:str/0/str, r_mapping:dict/0/? · returned Tensor · level recorded 2026-09-24
get_emb_centers pseudo_labeling.py ran no licence file found · pointer only · 1fbd2c69b401c975 · report fixture: signature embeddings:Tensor/2/float, label_array:Tensor/1/int, n_label:int/0/int · returned Tensor · level recorded 2026-09-24
rynewu224/GraphDA found in paper text by Syntology 13 samples, 8 ran (2 instrument-failed) · 5 unverified
DGDA_loss optimize.py ran no licence file found · pointer only · 6152b7266d197c0b · report fixture: signature res:dict/0/?, labels:Tensor/1/int, adj:Tensor/3/float, domain:int/0/int, weights:tuple/1/Tensor, manipulate:bool/0/bool, dadj:Tensor/3/float · returned Tensor · level recorded 2026-09-24
DGDA_m_loss optimize.py ran no licence file found · pointer only · f43770101f1f3229 · report fixture: signature res:dict/0/?, labels:Tensor/1/int, adj:Tensor/3/float, domain:int/0/int, weights:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
DSR_loss optimize.py ran no licence file found · pointer only · e19363b29126ec89 · report fixture: signature res:dict/0/?, labels:Tensor/1/int, adj:Tensor/3/float, domain:int/0/int, weights:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
drop_edges utils.py ran no licence file found · pointer only · 259d9f9326d3bbfd · report fixture: signature adj:Tensor/3/float, drop_rate:float/0/float, add_rate:float/0/float · returned tuple · level recorded 2026-09-24
get_metrics in 46 papers utils.py ran fingerprinted no licence file found · pointer only · 7957f349f88f21ca · report fixture: signature y_true:ndarray/1/int, y_score:ndarray/1/float · returned tuple · level recorded 2026-09-24
grad_reverse in 35 papers
census: 12 implementations from 17 papers, 1 distinct output on one shared input
layers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 12b63b50bbdf9a59 · report fixture: signature x:Tensor/2/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-24
load_influence_dataset data_loader.py ran no licence file found · pointer only · b5303b857ebe0e26 · report fixture: signature path:str/0/str, train_ratio:float/0/float, val_ratio:float/0/float, batch_size:int/0/int, shuffle:bool/0/bool, seed:int/0/int, num_workers:int/0/int · returned tuple · level recorded 2026-09-24
vectorized_sym_norm utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 2e83ba566e39edf7 · report fixture: signature adjs:Tensor/3/float · returned Tensor · level recorded 2026-09-24
evaluate in 514 papers run_dann.py unverified no licence file found · pointer only · e44b2f9346bef174 · report
evaluate in 514 papers run_dgda.py unverified no licence file found · pointer only · e11bd86d839000c0 · report
evaluate in 514 papers run_diva.py unverified no licence file found · pointer only · 687b820b60b21304 · report
evaluate in 514 papers run_dsr.py unverified no licence file found · pointer only · ccd766ebf0ae1ca0 · report
evaluate in 514 papers run_mdd.py unverified no licence file found · pointer only · b3b89ff191f4ffa5 · report
Graph-COM/Pair-Align found in paper text by Syntology 16 samples, 16 ran (7 instrument-failed) · 0 unverified
BCE_loss src/utils.py ran · our draft was wrong MIT (permissive) · 26f762cdf5ca4d94 · report fixture: signature pred:Tensor/2/float, label:Tensor/2/int · returned Tensor · level recorded 2026-09-24
CE_loss in 5 papers src/utils.py ran · our draft was wrong MIT (permissive) · 9c13510193b49939 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/float · returned Tensor · level recorded 2026-09-24
CSBM data_process/pre_datasets.py ran MIT (permissive) · 595ba30726d93400 · report fixture: signature setting:str/0/str, SIGMA:float/0/float · returned Data · level recorded 2026-09-24
LS_optimization src/calc_rw.py ran · our draft was wrong MIT (permissive) · ebef98525e89e8a8 · report fixture: signature cov:Tensor/2/float, muhat_tgt:Tensor/1/float, mu_src:Tensor/1/float, lambda_reg:float/0/float · returned ndarray · level recorded 2026-09-22
buildConnections data_process/prepare_pileup.py ran · honoured contract fingerprinted MIT (permissive) · c2f6ec3f0bfff768 · report fixture: signature eta:ndarray/1/float, phi:ndarray/1/float · returned tuple · level recorded 2026-09-24
build_optimizer in 83 papers src/utils.py ran MIT (permissive) · 2b9657e01a8cd076 · report fixture: signature args:Args/0/?, params:generator/0/? · returned tuple · level recorded 2026-09-24
cal_Median_LeftRMS data_process/prepare_pileup.py ran · honoured contract fingerprinted MIT (permissive) · a93838a6790aa900 · report fixture: signature x:ndarray/1/float · returned tuple · level recorded 2026-09-24
calc_edge_rw_pseudo src/calc_rw.py ran · our draft was wrong MIT (permissive) · 56ebe258e5e4e252 · report fixture: signature src_graph:SimpleGraph/0/?, tgt_graph:SimpleGraph/0/?, yhat_src:Tensor/2/float, yhat_tgt:Tensor/2/float, device:device/0/?, args:ArgsConfig/0/? · returned tuple · level recorded 2026-09-24
calc_ratio_weight src/calc_rw.py ran · our draft was wrong MIT (permissive) · 3314a8dc8f22a69d · report fixture: signature src_graph:MockGraph/0/?, kmm_weight:ndarray/1/float, gamma_reg:float/0/float · returned tuple · level recorded 2026-09-22
edgeidx_to_adj data_process/pre_datasets.py ran · our draft was wrong MIT (permissive) · 9e480bc71d643ce7 · report fixture: signature edge_source:ndarray/1/int, edge_target:ndarray/1/int, num_node:int/0/int · returned csr_matrix · level recorded, date not recorded
edges_to_adj in 5 papers data_process/pre_datasets.py ran · our draft was wrong MIT (permissive) · b303d995f3e0d28e · report fixture: signature edges:list/1/list, num_node:int/0/int · returned tuple · level recorded, date not recorded
edges_to_adj in 5 papers data_process/prepare_pileup.py ran MIT (permissive) · adad8a0f35142eb0 · report fixture: signature edge_source:ndarray/1/int, edge_target:ndarray/1/int, num_node:int/0/int · returned csr_matrix · level recorded 2026-09-24
load_nc_dataset data_process/pre_arxiv.py ran MIT (permissive) · 32b454f2035d61f4 · report fixture: signature data_dir:str/0/str, dataname:str/0/str, year:list/1/int · returned MockOGBDataset · level recorded 2026-09-24
load_ogb_arxiv data_process/pre_arxiv.py ran MIT (permissive) · 2d2a8de7147f5a42 · report fixture: signature data_dir:str/0/str, year_bound:list/1/int, proportion:float/0/float · returned MockNodePropPredDataset · level recorded 2026-09-24
rewrite_tensor data_process/gen_spr_graph.py ran MIT (permissive) · b9fd25bb3fad3172 · report fixture: signature tensor:CustomTensor/0/?, mappings:dict/0/? · returned CustomTensor · level recorded 2026-09-24
take_second data_process/pre_arxiv.py ran · honoured contract fingerprinted MIT (permissive) · 75b35bd6fdaaf274 · report fixture: signature element:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24

Tasks

BenchmarkingDomain AdaptationGRAPH DOMAIN ADAPTATION

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