Papers › Global Attention Improves Graph Networks Generalization

Global Attention Improves Graph Networks Generalization

14 Jun 2020arXiv:2006.07846archive 2025-07-28

Omri Puny, Heli Ben-Hamu, Yaron Lipman

This paper advocates incorporating a Low-Rank Global Attention (LRGA) module, a computation and memory efficient variant of the dot-product attention (Vaswani et al., 2017), to Graph Neural Networks (GNNs) for improving their generalization power. To theoretically quantify the generalization properties granted by adding the LRGA module to GNNs, we focus on a specific family of expressive GNNs and show that augmenting it with LRGA provides algorithmic alignment to a powerful graph isomorphism test, namely the 2-Folklore Weisfeiler-Lehman (2-FWL) algorithm. In more detail we: (i) consider the recent Random Graph Neural Network (RGNN) (Sato et al., 2020) framework and prove that it is universal in probability; (ii) show that RGNN augmented with LRGA aligns with 2-FWL update step via polynomial kernels; and (iii) bound the sample complexity of the kernel's feature map when learned with a randomly initialized two-layer MLP. From a practical point of view, augmenting existing GNN layers with LRGA produces state of the art results in current GNN benchmarks. Lastly, we observe that augmenting various GNN architectures with LRGA often closes the performance gap between different models.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2006.07846")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 4 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chuanqichen/cs224w mentioned on GitHubpytorch report
omri1348/LRGA mentioned on GitHubpytorch report
omri1348/LRGA 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

4 samples harvested; 4 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it

Licence: 4 of the 4 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 omri1348/LRGA. “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.

gpu_setup omri1348/LRGA/ogb/examples/linkproppred/collab/gnn.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 01da28167d92f23a · report
joint_normalize2 omri1348/LRGA/ogb/examples/linkproppred/collab/graph_global_attention_layer.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 7d01f508ca84b432 · report
test omri1348/LRGA/ogb/examples/linkproppred/collab/gnn.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · aed917122fd597e7 · report
train omri1348/LRGA/ogb/examples/linkproppred/collab/gnn.py community (archive-listed) ran · honoured contract no licence file found · pointer only · a2328b5e3445a490 · report

Tasks

Graph Neural Network

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-collab PLNLP+ LRGA Ext. data No #7 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP+ LRGA Number of params 35200656 #7 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP+ LRGA Test Hits@50 0.6909 ± 0.0055 #7 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP+ LRGA Validation Hits@50 1.0000 ± 0.0000 #7 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab LRGA + GCN Ext. data No #23 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab LRGA + GCN Number of params 1069489 #23 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab LRGA + GCN Test Hits@50 0.5221 ± 0.0072 #23 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab LRGA + GCN Validation Hits@50 0.6088 ± 0.0059 #23 of 34 Archive leaderboard report
Link Property Prediction ogbl-ddi LRGA + GCN Ext. data No #20 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi LRGA + GCN Number of params 1576081 #20 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi LRGA + GCN Test Hits@20 0.6230 ± 0.0912 #20 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi LRGA + GCN Validation Hits@20 0.6675 ± 0.0058 #20 of 31 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

Graph Neural Network

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