Papers › Topology-Informed Graph Transformer

Topology-Informed Graph Transformer

3 Feb 2024arXiv:2402.02005archive 2025-07-28

Yun Young Choi, Sun Woo Park, Minho Lee, Youngho Woo

Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs). One key challenge in enhancing graph transformers is strengthening the discriminative power of distinguishing isomorphisms of graphs, which plays a crucial role in boosting their predictive performances. To address this challenge, we introduce 'Topology-Informed Graph Transformer (TIGT)', a novel transformer enhancing both discriminative power in detecting graph isomorphisms and the overall performance of Graph Transformers. TIGT consists of four components: A topological positional embedding layer using non-isomorphic universal covers based on cyclic subgraphs of graphs to ensure unique graph representation: A dual-path message-passing layer to explicitly encode topological characteristics throughout the encoder layers: A global attention mechanism: And a graph information layer to recalibrate channel-wise graph features for better feature representation. TIGT outperforms previous Graph Transformers in classifying synthetic dataset aimed at distinguishing isomorphism classes of graphs. Additionally, mathematical analysis and empirical evaluations highlight our model's competitive edge over state-of-the-art Graph Transformers across various benchmark datasets.

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 21 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 5 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

leemingo/tigt officialmentioned on GitHubpytorchSyntology: 11 samples, 8 ran (2 instrument-failed) · 3 unverified report
leemingo/cy2mixer mentioned on GitHubpytorchSyntology: 10 samples, 9 ran (2 instrument-failed) · 1 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

21 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 5 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 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.

2ran · honoured contract
5ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
6ran
4unverified

Licence: 21 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 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”. “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.

leemingo/tigt official repository 11 samples, 8 ran (2 instrument-failed) · 3 unverified
default in 430 papers graphgps/layer/performer_layer.py ran · violated contract fingerprinted no licence file found · pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
empty in 9 papers graphgps/layer/performer_layer.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 19925529d217754e · report fixture: signature tensor:Tensor/2/float · returned bool · level recorded 2026-09-24
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
graphgps/layer/performer_layer.py ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_final_pretrained_ckpt in 28 papers graphgps/finetuning.py ran · our draft was wrong no licence file found · pointer only · 1bb331bf70a78136 · report fixture: signature ckpt_dir:str/0/str · returned str · level recorded 2026-09-24
get_log_deg in 7 papers graphgps/network/tigt.py ran · honoured contract no licence file found · pointer only · a1c29ec4fe872b3b · report fixture: signature batch:callable/0/? · returned Tensor · level recorded 2026-09-24
is_seed in 16 papers graphgps/agg_runs.py ran · violated contract no licence file found · pointer only · c98a702be0660ac9 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-25
is_split in 17 papers graphgps/agg_runs.py ran · violated contract no licence file found · pointer only · 438635c08adfe2aa · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-25
join_list in 19 papers graphgps/agg_runs.py ran fingerprinted no licence file found · pointer only · 40e98e1ecbf39f34 · report fixture: signature l1:list/1/Tensor, l2:list/1/Tensor · returned list · level recorded 2026-09-25
apply_chunking_to_forward in 25 papers graphgps/layer/bigbird_layer.py unverified no licence file found · pointer only · ae56bcfaae96da3c · report
init_model_from_pretrained in 28 papers graphgps/finetuning.py unverified no licence file found · pointer only · 3db4474abe13fdee · report
load_pretrained_model_cfg in 27 papers graphgps/finetuning.py unverified no licence file found · pointer only · d796cdea5889c847 · report
leemingo/cy2mixer community (archive-listed) 10 samples, 9 ran (2 instrument-failed) · 1 unverified
MAE in 46 papers lib/metrics.py ran fingerprinted no licence file found · pointer only · 561509b199175ea9 · report fixture: signature y_true:ndarray/1/float, y_pred:ndarray/1/float · returned float32 · level recorded 2026-09-24
MSE in 28 papers lib/metrics.py ran fingerprinted no licence file found · pointer only · 0a7d2992d05685eb · report fixture: signature y_true:ndarray/2/float, y_pred:ndarray/2/float · returned float32 · level recorded 2026-09-24
RMSE in 15 papers lib/metrics.py ran · violated contract fingerprinted no licence file found · pointer only · 602913d134538363 · report fixture: signature y_true:ndarray/1/float, y_pred:ndarray/1/float · returned float32 · level recorded 2026-09-24
data_load in 15 papers model/Cy2C_utils.py ran no licence file found · pointer only · 28d0813e58ab4fd5 · report fixture: signature dataset:SimpleDataset/0/?, normalize:bool/0/bool, option:int/0/int · returned SimpleDataset · level recorded 2026-09-24
load_pickle in 115 papers lib/utils.py ran · our draft was wrong no licence file found · pointer only · cd17080a788963f3 · report fixture: signature pickle_file:str/0/str · returned dict · level recorded 2026-09-24
make_cycle_adj_speed_nosl model/Cy2C_utils.py ran no licence file found · pointer only · 4a5dc6b540cf0d4f · report fixture: signature raw_list_adj:list/1/list, data:callable/0/? · returned tuple · level recorded 2026-09-24
masked_mae_loss in 7 papers lib/utils.py ran fingerprinted no licence file found · pointer only · 3c39e4ce38e253db · report fixture: signature preds:Tensor/2/float, labels:Tensor/2/float, null_val:float/0/float · returned Tensor · level recorded 2026-09-24
max_node_dataset model/Cy2C_utils.py ran · honoured contract no licence file found · pointer only · e5d90ec7d5feae99 · report fixture: signature dataset:MockDataset/0/? · returned int64 · level recorded 2026-09-24
vrange lib/utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · e7de63c9d9975208 · report fixture: signature starts:ndarray/1/int, stops:ndarray/1/int · returned ndarray · level recorded 2026-09-24
get_dataloaders_from_index_data lib/data_prepare.py unverified no licence file found · pointer only · 0252438018c7afc0 · report

Tasks

Graph ClassificationGraph RegressionInductive BiasNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification CIFAR10 100k TIGT Accuracy (%) 73.955 #8 of 20 Archive leaderboard report
Graph Classification MNIST TIGT Accuracy 98.230±0.133 #9 of 13 Archive leaderboard report
Graph Classification Peptides-func TIGT AP 0.6679 #25 of 44 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC TIGT Validation MAE 0.0826 #7 of 20 Archive leaderboard report
Graph Regression Peptides-struct TIGT MAE 0.2485 #19 of 39 Archive leaderboard report
Graph Regression ZINC TIGT MAE 0.057 #3 of 27 Archive leaderboard report
Graph Regression ZINC-full TIGT Test MAE 0.014 #3 of 19 Archive leaderboard report
Node Classification CLUSTER TIGT Accuracy 78.033 #8 of 12 Archive leaderboard report
Node Classification PATTERN TIGT Accuracy 86.680 #10 of 11 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