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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.02005")

Code

Syntology Ran 14 of 21 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · violated contract; 12 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 5 ran; community (archive-listed): 10 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

leemingo/tigt officialmentioned on GitHubpytorch report
leemingo/cy2mixer mentioned on GitHubpytorch 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; 14 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
12ran
7unverified

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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

default leemingo/tigt/graphgps/layer/performer_layer.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 60fff7c3c400d7ff · report
empty leemingo/tigt/graphgps/layer/performer_layer.py official repository ran fingerprinted no licence file found · pointer only · 19925529d217754e · report
exists leemingo/tigt/graphgps/layer/performer_layer.py official repository ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report
get_final_pretrained_ckpt leemingo/tigt/graphgps/finetuning.py official repository ran no licence file found · pointer only · 1bb331bf70a78136 · report
get_log_deg leemingo/tigt/graphgps/network/tigt.py official repository ran no licence file found · pointer only · a1c29ec4fe872b3b · report
apply_chunking_to_forward leemingo/tigt/graphgps/layer/bigbird_layer.py official repository unverified no licence file found · pointer only · ae56bcfaae96da3c · report
init_model_from_pretrained leemingo/tigt/graphgps/finetuning.py official repository unverified no licence file found · pointer only · 3db4474abe13fdee · report
is_seed leemingo/tigt/graphgps/agg_runs.py official repository unverified no licence file found · pointer only · c98a702be0660ac9 · report
is_split leemingo/tigt/graphgps/agg_runs.py official repository unverified no licence file found · pointer only · 438635c08adfe2aa · report
join_list leemingo/tigt/graphgps/agg_runs.py official repository unverified no licence file found · pointer only · 40e98e1ecbf39f34 · report
load_pretrained_model_cfg leemingo/tigt/graphgps/finetuning.py official repository unverified no licence file found · pointer only · d796cdea5889c847 · report
MAE leemingo/cy2mixer/lib/metrics.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 561509b199175ea9 · report
MSE leemingo/cy2mixer/lib/metrics.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 0a7d2992d05685eb · report
RMSE leemingo/cy2mixer/lib/metrics.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 602913d134538363 · report
data_load leemingo/cy2mixer/model/Cy2C_utils.py community (archive-listed) ran no licence file found · pointer only · 28d0813e58ab4fd5 · report
load_pickle leemingo/cy2mixer/lib/utils.py community (archive-listed) ran no licence file found · pointer only · cd17080a788963f3 · report
make_cycle_adj_speed_nosl leemingo/cy2mixer/model/Cy2C_utils.py community (archive-listed) ran no licence file found · pointer only · 4a5dc6b540cf0d4f · report
masked_mae_loss leemingo/cy2mixer/lib/utils.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 3c39e4ce38e253db · report
max_node_dataset leemingo/cy2mixer/model/Cy2C_utils.py community (archive-listed) ran no licence file found · pointer only · e5d90ec7d5feae99 · report
vrange leemingo/cy2mixer/lib/utils.py community (archive-listed) ran no licence file found · pointer only · e7de63c9d9975208 · report
get_dataloaders_from_index_data leemingo/cy2mixer/lib/data_prepare.py community (archive-listed) 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