Papers › Transformers over Directed Acyclic Graphs

Transformers over Directed Acyclic Graphs

24 Oct 2022NeurIPS 2023 11arXiv:2210.13148archive 2025-07-28

Yuankai Luo, Veronika Thost, Lei Shi

Transformer models have recently gained popularity in graph representation learning as they have the potential to learn complex relationships beyond the ones captured by regular graph neural networks. The main research question is how to inject the structural bias of graphs into the transformer architecture, and several proposals have been made for undirected molecular graphs and, recently, also for larger network graphs. In this paper, we study transformers over directed acyclic graphs (DAGs) and propose architecture adaptations tailored to DAGs: (1) An attention mechanism that is considerably more efficient than the regular quadratic complexity of transformers and at the same time faithfully captures the DAG structure, and (2) a positional encoding of the DAG's partial order, complementing the former. We rigorously evaluate our approach over various types of tasks, ranging from classifying source code graphs to nodes in citation networks, and show that it is effective in two important aspects: in making graph transformers generally outperform graph neural networks tailored to DAGs and in improving SOTA graph transformer performance in terms of both quality and efficiency.

PaperPDFConference PDFCodeCode 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="2210.13148")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · honoured contract.

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

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

9 samples harvested; 2 ran; 2 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 · honoured contract
7unverified

Licence: 0 of the 9 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 LUOyk1999/DAGformer. “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.

create_products_of_givens_rotations LUOyk1999/DAGformer/Node_classification_citation/dag_nodeformer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 214d66f90baa5770 · report
create_projection_matrix LUOyk1999/DAGformer/Node_classification_citation/dag_nodeformer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 44fbc869db4685a6 · report
eigvec_normalizer LUOyk1999/DAGformer/NA/src/utils_dag.py community (archive-listed) unverified MIT (permissive) · 0ca4bfed1ccd10c3 · report
get_conv LUOyk1999/DAGformer/self-citation/models.py community (archive-listed) unverified MIT (permissive) · 19afc55973cf4ff3 · report
get_lap_decomp_stats LUOyk1999/DAGformer/NA/src/utils_dag.py community (archive-listed) unverified MIT (permissive) · 3f612bede595ee34 · report
get_simple_gnn_layer LUOyk1999/DAGformer/Node_classification_citation/gnn_layers.py community (archive-listed) unverified MIT (permissive) · a99c1bcf4a331aae · report
get_simple_gnn_layer LUOyk1999/DAGformer/NA/dvae/gnn_layers.py community (archive-listed) unverified MIT (permissive) · 8b08a2aa35ad4509 · report
relu_kernel_transformation LUOyk1999/DAGformer/Node_classification_citation/dag_nodeformer.py community (archive-listed) unverified MIT (permissive) · 9ec77c43b56275a8 · report
top_sort LUOyk1999/DAGformer/NA/src/utils_dag.py community (archive-listed) unverified MIT (permissive) · 9dd505688b70e6d7 · report

Tasks

Graph Property PredictionGraph Representation LearningRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction ogbg-code2 DAGformer Ext. data No #3 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 DAGformer Number of params 14952882 #3 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 DAGformer Test F1 score 0.2018 ± 0.0021 #3 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 DAGformer Validation F1 score 0.1846 ± 0.0010 #3 of 21 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.

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