Papers › Graph Inductive Biases in Transformers without Message Passing

Graph Inductive Biases in Transformers without Message Passing

27 May 2023arXiv:2305.17589archive 2025-07-28

Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biases are more crucial. To bridge this gap, we propose the Graph Inductive bias Transformer (GRIT) -- a new Graph Transformer that incorporates graph inductive biases without using message passing. GRIT is based on several architectural changes that are each theoretically and empirically justified, including: learned relative positional encodings initialized with random walk probabilities, a flexible attention mechanism that updates node and node-pair representations, and injection of degree information in each layer. We prove that GRIT is expressive -- it can express shortest path distances and various graph propagation matrices. GRIT achieves state-of-the-art empirical performance across a variety of graph datasets, thus showing the power that Graph Transformers without message-passing can deliver.

PaperPDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 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: 10 samples from 1 repository, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

liamma/grit officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 6 ran (4 instrument-failed) · 4 unverified report
linusbao/MoSE mentioned on GitHubpytorchSyntology: 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

12 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 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.

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

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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.

liamma/grit official repository 10 samples, 6 ran (4 instrument-failed) · 4 unverified
accuracy_SBM in 8 papers grit/logger.py ran; the contract check could not run (RAISES) MIT (permissive) · ecf14287d3465c48 · report fixture: signature targets:Tensor/1/int, pred_int:ndarray/1/int · returned float64 · level recorded 2026-09-24
eval_spearmanr in 7 papers grit/logger.py ran · our draft was wrong fingerprinted MIT (permissive) · 9dc78001d467fc9d · report fixture: signature y_true:ndarray/1/float, y_pred:ndarray/1/float · returned dict · level recorded 2026-09-24
get_final_pretrained_ckpt in 28 papers grit/finetuning.py ran · our draft was wrong MIT (permissive) · 1bb331bf70a78136 · report fixture: signature ckpt_dir:str/0/str · returned str · level recorded 2026-09-24
get_log_deg in 7 papers grit/layer/grit_layer.py ran · honoured contract MIT (permissive) · b5c9e7acf599a98a · report fixture: signature batch:MinimalBatch/0/? · returned Tensor · level recorded 2026-09-24
init_model_from_pretrained in 28 papers grit/finetuning.py ran MIT (permissive) · 9e4db46ba20af98e · report fixture: signature model:callable/0/?, pretrained_dir:str/0/str, freeze_main:bool/0/bool, reset_prediction_head:bool/0/bool · returned SimpleModel · level recorded 2026-09-24
subtoken_cross_entropy grit/loss/subtoken_prediction_loss.py ran · our draft was wrong MIT (permissive) · 47e492109e6d308f · report fixture: signature pred_list:list/1/Tensor, true:dict/0/? · returned tuple · level recorded 2026-09-24
adj_l1_losses grit/loss/adj.py unverified MIT (permissive) · dc82c18c9d42c1c1 · report
l1_losses in 7 papers grit/loss/l1.py unverified MIT (permissive) · d59c374db2cf64ae · report
load_pretrained_model_cfg in 27 papers grit/finetuning.py unverified MIT (permissive) here; the stored copy is pointer only · 91c1f5bb90bbe0f3 · report
multilabel_cross_entropy in 8 papers grit/loss/multilabel_classification_loss.py unverified MIT (permissive) · f1cbbbc857d8b871 · report
linusbao/MoSE community (archive-listed) 2 samples, 0 ran · 2 unverified
FeatureEncoder in 9 papers GRIT/grit/network/grit_model.py unverified MIT (permissive) · 932e8da6cc45ebfc · report
GritTransformer GRIT/grit/network/grit_model.py unverified MIT (permissive) · 8afca3460aa00ce7 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Graph Inductive bias Transformer (GRIT) (graph method: Graph Inductive bias Transformer (GRIT)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

  1. GritTransformer entry · level 0 · unverified · 8afca3460aa00ce7
  2. FeatureEncoder helper · level 0 · unverified · 932e8da6cc45ebfc

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.17589") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph ClassificationGraph RegressionInductive BiasNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification CIFAR10 100k GRIT Accuracy (%) 76.468 #4 of 20 Archive leaderboard report
Graph Classification MNIST GRIT Accuracy 98.108 #11 of 13 Archive leaderboard report
Graph Classification Peptides-func GRIT AP 0.6988±0.0082 #14 of 44 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC GRIT Validation MAE 0.0859 #11 of 20 Archive leaderboard report
Graph Regression Peptides-struct GRIT MAE 0.2460±0.0012 #10 of 39 Archive leaderboard report
Graph Regression ZINC GRIT MAE 0.059 #4 of 27 Archive leaderboard report
Graph Regression ZINC-500k GRIT MAE 0.059 #4 of 36 Archive leaderboard report
Graph Regression ZINC-full GRIT Test MAE 0.023 #6 of 19 Archive leaderboard report
Node Classification CLUSTER GRIT Accuracy 80.026 #1 of 12 Archive leaderboard report
Node Classification PATTERN GRIT Accuracy 87.196 #2 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