Papers › DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

11 Nov 2021NeurIPS 2021 12arXiv:2111.06283archive 2025-07-28

Pál András Papp, Karolis Martinkus, Lukas Faber, Roger Wattenhofer

This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly and independently dropped in each of these runs. Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs. We derive theoretical bounds for the number of runs required to ensure a reliable distribution of dropouts, and we prove several properties regarding the expressive capabilities and limits of DropGNNs. We experimentally validate our theoretical findings on expressiveness. Furthermore, we show that DropGNNs perform competitively on established GNN benchmarks.

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="2111.06283")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: official repository: 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

karolismart/dropgnn officialmentioned in papermentioned on GitHubpytorchMIT 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

3 samples harvested; 0 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.

3unverified

Licence: 0 of the 3 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 karolismart/dropgnn. “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.

S2V_to_PyG karolismart/dropgnn/ptc_dataset.py official repository unverified MIT (permissive) · ca79c0c0249b5487 · report
load_data karolismart/dropgnn/ptc_dataset.py official repository unverified MIT (permissive) · 22f66d8c36eceac7 · report
main karolismart/dropgnn/gin-synthetic.py official repository unverified MIT (permissive) · 0245c4edf22b808d · report

Tasks

Graph ClassificationGraph RegressionMolecular Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification D&D DropGIN Accuracy 78.151±3.711 #29 of 53 Archive leaderboard report
Graph Classification ENZYMES DropGIN Accuracy 65.128±4.117 #22 of 54 Archive leaderboard report
Graph Classification IMDb-B DropGIN Accuracy 75.7% #21 of 51 Archive leaderboard report
Graph Classification IMDb-M DropGIN Accuracy 51.4% #15 of 36 Archive leaderboard report
Graph Classification MUTAG DropGIN Accuracy 90.4% #21 of 74 Archive leaderboard report
Graph Classification NCI1 DropGIN Accuracy 84.331±1.564 #21 of 69 Archive leaderboard report
Graph Classification NCI109 DropGIN Accuracy 83.961±1.141 #8 of 38 Archive leaderboard report
Graph Classification PROTEINS DropGIN Accuracy 76.3% #52 of 103 Archive leaderboard report
Graph Classification PTC DropGIN Accuracy 66.3% #19 of 37 Archive leaderboard report
Graph Regression ESR2 DropGIN R2 0.675±0.000 #3 of 9 Archive leaderboard report
Graph Regression ESR2 DropGIN RMSE 0.503±0.675 #3 of 9 Archive leaderboard report
Graph Regression F2 DropGIN R2 0.886±0.000 #5 of 9 Archive leaderboard report
Graph Regression F2 DropGIN RMSE 0.343±0.886 #5 of 9 Archive leaderboard report
Graph Regression KIT GINDrop R2 0.835±0.000 #3 of 9 Archive leaderboard report
Graph Regression KIT GINDrop RMSE 0.441±0.835 #3 of 9 Archive leaderboard report
Graph Regression Lipophilicity DropGIN R2 0.809±0.008 #6 of 23 Archive leaderboard report
Graph Regression Lipophilicity DropGIN RMSE 0.552±0.012 #6 of 23 Archive leaderboard report
Graph Regression PARP1 DropGIN R2 0.920±0.000 #5 of 9 Archive leaderboard report
Graph Regression PARP1 DropGIN RMSE 0.354±0.920 #5 of 9 Archive leaderboard report
Graph Regression PGR GINDrop R2 0.702±0.000 #3 of 9 Archive leaderboard report
Graph Regression PGR GINDrop RMSE 0.527±0.702 #3 of 9 Archive leaderboard report
Molecular Property Prediction ESOL DropGIN R2 0.935±0.012 #5 of 20 Archive leaderboard report
Molecular Property Prediction ESOL DropGIN RMSE 0.520±0.048 #5 of 20 Archive leaderboard report
Molecular Property Prediction FreeSolv DropGIN R2 0.972±0.005 #2 of 22 Archive leaderboard report
Molecular Property Prediction FreeSolv DropGIN RMSE 0.657±0.059 #2 of 22 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

Dropout

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