Papers › Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity...

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity

18 Aug 2023arXiv:2308.09517archive 2025-07-28

Van Thuy Hoang, O-Joun Lee

Graph representation learning (GRL) methods, such as graph neural networks and graph transformer models, have been successfully used to analyze graph-structured data, mainly focusing on node classification and link prediction tasks. However, the existing studies mostly only consider local connectivity while ignoring long-range connectivity and the roles of nodes. In this paper, we propose Unified Graph Transformer Networks (UGT) that effectively integrate local and global structural information into fixed-length vector representations. First, UGT learns local structure by identifying the local substructures and aggregating features of the k-hop neighborhoods of each node. Second, we construct virtual edges, bridging distant nodes with structural similarity to capture the long-range dependencies. Third, UGT learns unified representations through self-attention, encoding structural distance and p-step transition probability between node pairs. Furthermore, we propose a self-supervised learning task that effectively learns transition probability to fuse local and global structural features, which could then be transferred to other downstream tasks. Experimental results on real-world benchmark datasets over various downstream tasks showed that UGT significantly outperformed baselines that consist of state-of-the-art models. In addition, UGT reaches the expressive power of the third-order Weisfeiler-Lehman isomorphism test (3d-WL) in distinguishing non-isomorphic graph pairs. The source code is available at https://github.com/NSLab-CUK/Unified-Graph-Transformer.

PaperPDFCodeCode 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

Syntology 26 code samples harvested from 3 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 20 samples from 2 repositories, 16 ran (12 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nslab-cuk/unified-graph-transformer officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 3 ran (2 instrument-failed) · 3 unverified report
nslab-cuk/community-aware-graph-transformer mentioned on GitHubpytorchMITSyntology: 18 samples, 16 ran (4 instrument-failed) · 2 unverified report
nslab-cuk/literalkg mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 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: 19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 7 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.

6ran · our draft was wrong
13ran
7unverified

Licence: 0 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 3 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.

nslab-cuk/unified-graph-transformer official repository 6 samples, 3 ran (2 instrument-failed) · 3 unverified
imp_exp_attn in 6 papers Graph_classification/layers/graph_transformer_edge_layer.py ran MIT (permissive) · 700de849477f93ce · report fixture: signature implicit_attn:str/0/str, explicit_edge:str/0/str · returned function · level recorded 2026-09-24
scaled_exp in 5 papers Graph_classification/layers/graph_transformer_layer.py ran · our draft was wrong MIT (permissive) · 654acacaf00954fb · report fixture: signature field:str/0/str, scale_constant:float/0/float · returned function · level recorded 2026-09-22
scaling in 16 papers Graph_classification/layers/graph_transformer_edge_layer.py ran · our draft was wrong MIT (permissive) · a3fb87a259b15eae · report fixture: signature field:str/0/str, scale_constant:float/0/float · returned function · level recorded 2026-09-24
build_multigraph_from_layers Graph_classification/build_multigraph.py unverified MIT (permissive) · 92c17eab0627285b · report
exp in 11 papers Graph_classification/models.py unverified MIT (permissive) · 5a6826903f8b965a · report
src_dot_dst in 11 papers Graph_classification/layers/graph_transformer_edge_layer.py unverified MIT (permissive) · 9408c2ca6e799410 · report
nslab-cuk/community-aware-graph-transformer community (archive-listed) 18 samples, 16 ran (4 instrument-failed) · 2 unverified
DigitizeY gnnutils.py ran · our draft was wrong MIT (permissive) · be384a8aa916b3d6 · report fixture: signature pyg_data:MockPyGData/0/? · returned MockPyGData · level recorded 2026-09-26
GetProbTranMat util.py ran fingerprinted MIT (permissive) · 3910837ba82ef07e · report fixture: signature Ak:ndarray/2/float, num_node:int/0/int · returned ndarray · level recorded 2026-09-24
MAE in 46 papers metrics.py ran fingerprinted MIT (permissive) · 8c3fd13fe72b290d · report fixture: signature scores:Tensor/2/float, targets:Tensor/2/float · returned float · level recorded 2026-09-25
accuracy_MNIST_CIFAR metrics.py ran MIT (permissive) · b202433545bfeddd · report fixture: signature scores:Tensor/2/float, targets:Tensor/1/int · returned float · level recorded 2026-09-25
accuracy_TU metrics.py ran MIT (permissive) · f064ff3b4454d19d · report fixture: signature scores:Tensor/2/float, targets:Tensor/1/int · returned float · level recorded 2026-09-25
check_rm datasets/bgp.py ran MIT (permissive) · f6a38e82cb7bacde · report fixture: signature neighbors_set:set/0/?, unlabeled_nodes:set/0/? · returned bool · level recorded 2026-09-25
convert_ndarray datasets/bgp.py ran MIT (permissive) · 7984390414b770ba · report fixture: signature x:dict/0/? · returned ndarray · level recorded 2026-09-26
exp in 11 papers models.py ran MIT (permissive) · 157006cf12196817 · report fixture: signature field:str/0/str · returned function · level recorded 2026-09-24
filter_rels exp.py ran · our draft was wrong MIT (permissive) · 5e3663ee66aeb1d8 · report fixture: signature data:MockData/0/?, r:int/0/int · returned MockData · level recorded 2026-09-22
getM_logM util.py ran MIT (permissive) · 7b2bf37d0a197712 · report fixture: signature nx_g:DiGraph/0/?, num_nodes:int/0/int, kstep:int/0/int · returned tuple · level recorded 2026-09-24
get_degrees datasets/airports.py ran MIT (permissive) · a093c2a5cfaf259d · report fixture: signature G:Graph/0/? · returned ndarray · level recorded 2026-09-26
get_distance in 25 papers util.py ran fingerprinted MIT (permissive) · f33dcc24274d2ad3 · report fixture: signature deg_A:float/0/float, deg_B:float/0/float · returned float64 · level recorded 2026-09-24
load_info in 7 papers exp.py ran MIT (permissive) · 5514e4d11d611865 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
mask_getitem dataset.py ran · our draft was wrong MIT (permissive) · 9a5805281d49fe0f · report fixture: signature self:MockSelf/0/?, datum:dict/0/? · returned MockDatum · level recorded 2026-09-26
rm_useless datasets/bgp.py ran MIT (permissive) · 4102c2d70e0e526f · report fixture: signature G:Graph/0/?, feats:ndarray/2/float, class_map:ndarray/1/int, unlabeled_nodes:list/1/int, num_layers:int/0/int · returned tuple · level recorded 2026-09-25
src_dot_dst in 11 papers models.py ran · our draft was wrong MIT (permissive) · 23fba400cff6fafa · report fixture: signature src_field:str/0/str, dst_field:str/0/str, out_field:str/0/str · returned function · level recorded 2026-09-22
even_quantile_labels in 21 papers dataset.py unverified MIT (permissive) · be162bddd27d9fac · report
load_Cora_ML gnnutils.py unverified MIT (permissive) · 699ec24a50a1213a · report
nslab-cuk/literalkg community (archive-listed) 2 samples, 0 ran · 2 unverified
fine_tuning_train main_finetuning.py unverified MIT (permissive) · 3d892bb81f72affb · report
fine_tuning_train main_finetuning_BCE.py unverified MIT (permissive) · 47ca8a31d787e6e4 · report

Tasks

Graph ClassificationGraph Representation LearningIsomorphism TestingLink PredictionNode ClassificationNode ClusteringRepresentation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification ENZYMES UGT Accuracy 67.22±3.92 #19 of 54 Archive leaderboard report
Graph Classification NCI1 UGT Accuracy 77.55 ±0.16% #42 of 69 Archive leaderboard report
Graph Classification NCI109 UGT Accuracy 75.45±1.26 #26 of 38 Archive leaderboard report
Graph Classification PROTEINS UGT Accuracy 80.12 ±0.32 #11 of 103 Archive leaderboard report
Node Classification Brazil Air-Traffic UGT Accuracy 0.8 ± 0.05 #1 of 7 Archive leaderboard report
Node Classification Chameleon UGT Accuracy 69.78 ±3.21 #32 of 61 Archive leaderboard report
Node Classification Citeseer UGT Accuracy 76.08±2.5 #15 of 71 Archive leaderboard report
Node Classification Cora UGT Accuracy 88.74±0.6% #6 of 73 Archive leaderboard report
Node Classification Cornell UGT Accuracy 70.0 ±4.44 #49 of 60 Archive leaderboard report
Node Classification Europe Air-Traffic UGT Accuracy 56.92 ±6.36 #1 of 7 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) UGT 1:1 Accuracy 36.84±0.62 #25 of 37 Archive leaderboard report
Node Classification Squirrel UGT Accuracy 66.96 ±2.49 #15 of 59 Archive leaderboard report
Node Classification Texas UGT Accuracy 86.67 ±8.31 #18 of 62 Archive leaderboard report
Node Classification USA Air-Traffic UGT Accuracy 66.22±4.55 #1 of 7 Archive leaderboard report
Node Classification Wisconsin UGT Accuracy 81.6 ±8.24 #49 of 63 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGraph TransformerLabel SmoothingLapEigenLaplacian PELayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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