Papers › Adaptive Universal Generalized PageRank Graph Neural Network

Adaptive Universal Generalized PageRank Graph Neural Network

14 Jun 2020ICLR 2021 1arXiv:2006.07988archive 2025-07-28

Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic

In many important graph data processing applications the acquired information includes both node features and observations of the graph topology. Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not optimally trade-off their utility and integrate them in a manner that is also universal. Here, universality refers to independence on homophily or heterophily graph assumptions. We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological information extraction, regardless of the extent to which the node labels are homophilic or heterophilic. Learned GPR weights automatically adjust to the node label pattern, irrelevant on the type of initialization, and thereby guarantee excellent learning performance for label patterns that are usually hard to handle. Furthermore, they allow one to avoid feature over-smoothing, a process which renders feature information nondiscriminative, without requiring the network to be shallow. Our accompanying theoretical analysis of the GPR-GNN method is facilitated by novel synthetic benchmark datasets generated by the so-called contextual stochastic block model. We also compare the performance of our GNN architecture with that of several state-of-the-art GNNs on the problem of node-classification, using well-known benchmark homophilic and heterophilic datasets. The results demonstrate that GPR-GNN offers significant performance improvement compared to existing techniques on both synthetic and benchmark data.

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="2006.07988")

Code

Syntology Ran 0 of 2 code samples harvested from 1 repository linked to this paper; 2 have no recorded run.

By repository: official repository: 2 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.

jianhao2016/GPRGNN officialmentioned in papermentioned 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

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 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.

2unverified

Licence: 2 of the 2 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 jianhao2016/gprgnn. “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.

GPRGNN jianhao2016/gprgnn/src/GNN_models.py official repository unverified no licence file found · pointer only · ddcec3dc58a4763f · report
GPR_prop jianhao2016/gprgnn/src/GNN_models.py official repository unverified no licence file found · pointer only · 82499cce1427e40b · report

Tasks

GPRGraph Neural NetworkNode ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsStochastic Block Model

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor GPRGCN Accuracy 35.16 ± 0.9 #47 of 62 Archive leaderboard report
Node Classification Chameleon GPRGCN Accuracy 62.59 ± 2.04 #49 of 61 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 67.48 ± 0.40 #15 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 67.63 ± 0.38 #31 of 33 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 77.13 ± 1.67 #11 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 87.95 ± 1.18 #13 of 26 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 79.51 ± 0.36 #29 of 33 Archive leaderboard report
Node Classification Cornell GPRGCN Accuracy 78.11 ± 6.55 #43 of 60 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 91.36 ± 0.70 #17 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 39.30 ± 0.27 #21 of 37 Archive leaderboard report
Node Classification Penn94 GPRGCN Accuracy 81.38 ± 0.16 #20 of 32 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 87.54 ± 0.38 #24 of 26 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 85.07 ± 0.09 #35 of 37 Archive leaderboard report
Node Classification Squirrel GPRGCN Accuracy 46.31 ± 2.46 #44 of 59 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 49.93 ± 0.53 #15 of 37 Archive leaderboard report
Node Classification Texas GPRGCN Accuracy 81.35 ± 5.32 #48 of 62 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 92.92 ± 0.61 #15 of 36 Archive leaderboard report
Node Classification Wisconsin GPRGCN Accuracy 82.55 ± 6.23 #48 of 63 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 93.75 ± 2.37 #15 of 35 Archive leaderboard report
Node Classification genius GPRGCN Accuracy 90.05 ± 0.31 #12 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 62.59 ± 2.04 #23 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) GPRGNN 1:1 Accuracy 67.48 ± 0.40 #12 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 78.11 ± 6.55 #20 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) GPRGNN 1:1 Accuracy 91.36 ± 0.70 #17 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) MLP-2 1:1 Accuracy 91.30 ± 0.70 #18 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe GPRGNN 1:1 Accuracy 66.90±0.50 #9 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GPRGCN 1:1 Accuracy 81.38 ± 0.16 #15 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 46.31 ± 2.46 #21 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 81.35 ± 5.32 #19 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) GPRGNN 1:1 Accuracy 92.92 ± 0.61 #14 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) MLP-2 1:1 Accuracy 92.26 ± 0.71 #16 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) GPRGCN 1:1 Accuracy 82.55 ± 6.23 #19 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) GPRGNN 1:1 Accuracy 93.75 ± 2.37 #15 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GPRGCN 1:1 Accuracy 90.05 ± 0.31 #14 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GPRGCN 1:1 Accuracy 61.89 ± 0.29 #21 of 26 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