Papers › Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning...

Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers

7 Feb 2024arXiv:2402.04538archive 2025-07-28

Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian

Graph transformers typically lack third-order interactions, limiting their geometric understanding which is crucial for tasks like molecular geometry prediction. We propose the Triplet Graph Transformer (TGT) that enables direct communication between pairs within a 3-tuple of nodes via novel triplet attention and aggregation mechanisms. TGT is applied to molecular property prediction by first predicting interatomic distances from 2D graphs and then using these distances for downstream tasks. A novel three-stage training procedure and stochastic inference further improve training efficiency and model performance. Our model achieves new state-of-the-art (SOTA) results on open challenge benchmarks PCQM4Mv2 and OC20 IS2RE. We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning. We also demonstrate the generality of TGT with SOTA results on the traveling salesman problem (TSP).

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="2402.04538")

Code

Syntology Ran 10 of 13 code samples harvested from 3 repositories linked to this paper; 3 have no recorded run. Of those that ran: 10 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 9 ran; community (archive-listed): 2 samples from 2 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shamim-hussain/tgt officialmentioned in papermentioned on GitHubpytorchMIT report
shamim-hussain/egt_pytorch mentioned on GitHubpytorch report
shamim-hussain/egt_triangular 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

13 samples harvested; 10 ran; 0 honoured the contract we drafted; 3 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.

10ran
3unverified

Licence: 0 of the 13 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; 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.

form_degree_scalers shamim-hussain/tgt/lib/tgt/layers/layers.py official repository ran MIT (permissive) · b18a7da4ce171c3d · report
geglu shamim-hussain/tgt/lib/tgt/layers/activations.py official repository ran MIT (permissive) · 46e9996c80897eae · report
glu shamim-hussain/tgt/lib/tgt/layers/activations.py official repository ran MIT (permissive) · ba1213011ced7cc9 · report
import_scheme shamim-hussain/tgt/lib/training/execute.py official repository ran MIT (permissive) · 99444cf6f6c68f14 · report
safe_load shamim-hussain/tgt/lib/training/config.py official repository ran MIT (permissive) · 76cce8eb1d1df68c · report
safe_load_str shamim-hussain/tgt/lib/training/config.py official repository ran fingerprinted MIT (permissive) · 600b01d18d7e780d · report
siglin shamim-hussain/tgt/lib/tgt/layers/triplet.py official repository ran MIT (permissive) · 9c6fd2a384f6f803 · report
str_presenter shamim-hussain/tgt/lib/training/config.py official repository ran MIT (permissive) · ec3a6e8533e97e72 · report
swiglu shamim-hussain/tgt/lib/tgt/layers/activations.py official repository ran MIT (permissive) · c724368b1b6a04e0 · report
get_configs_from_args shamim-hussain/tgt/lib/training/execute.py official repository unverified MIT (permissive) · 923e416970ed8684 · report
get_triplet_layer shamim-hussain/tgt/lib/tgt/layers/triplet.py official repository unverified MIT (permissive) · 3fe477d09a32f159 · report
EGT_Layer shamim-hussain/egt_pytorch/lib/models/egt_layers.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 3769fc037188340a · report
TripletAttention shamim-hussain/egt_triangular/lib/tgt/layers/triplet.py community (archive-listed) unverified MIT (permissive) · ad3053a477c51b49 · report

Tasks

Drug DiscoveryGraph LearningGraph Property PredictionGraph RegressionInitial Structure to Relaxed Energy (IS2RE), DirectLink PredictionMolecular Property PredictionPredictionProperty PredictionTransfer LearningTraveling Salesman Problem

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug Discovery LIT-PCBA(ALDH1) EGT+TGT-At-DP AUC 0.806 #1 of 4 Archive leaderboard report
Drug Discovery LIT-PCBA(KAT2A) EGT+TGT-At-DP AUC 0.746 #1 of 4 Archive leaderboard report
Drug Discovery LIT-PCBA(MAPK1) EGT+TGT-At-DP AUC 0.743 #1 of 4 Archive leaderboard report
Graph Property Prediction ogbg-molpcba TGT-Ag+TGT-At-DP Ext. data Yes #4 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba TGT-Ag+TGT-At-DP Number of params 47000000 #4 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba TGT-Ag+TGT-At-DP Test AP 0.3167 ± 0.0031 #4 of 36 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC TGT-At Test MAE 0.0683 #3 of 20 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC TGT-At Validation MAE 0.0671 #3 of 20 Archive leaderboard report
Link Prediction TSP/HCP Benchmark set TGT-Agx4 F1 0.871 #1 of 4 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 ConnectionSoftmaxTransformerTriplet Attention

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