Papers › Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

14 Oct 2018ICLR 2019 5arXiv:1810.05997archive 2025-07-28

Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend. In this paper, we use the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters on par or lower than previous models. It leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models. Our implementation is available online.

PaperPDFConference PDFCodeCode Syntology ran

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 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 11 ran (10 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

klicperajo/ppnp officialpytorchMITSyntology: 12 samples, 11 ran (1 instrument-failed) · 1 unverified report
benedekrozemberczki/APPNP mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
dmlc/dgl pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to node2vec: Scalable Feature Learning for Networks (arXiv:1607.00653; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified), Interaction Networks for Learning about Objects, Relations and Physics (arXiv:1612.00222; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result), Junction Tree Variational Autoencoder for Molecular Graph Generation (arXiv:1802.04364; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
dmlc/dgl pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to node2vec: Scalable Feature Learning for Networks (arXiv:1607.00653; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified), Interaction Networks for Learning about Objects, Relations and Physics (arXiv:1612.00222; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result), Junction Tree Variational Autoencoder for Molecular Graph Generation (arXiv:1802.04364; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
mahequn001/graphlearning mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How Attentive are Graph Attention Networks? (arXiv:2105.14491; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
10ran
1unverified

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 klicperajo/ppnp. “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.

klicperajo/ppnp official repository 12 samples, 11 ran (1 instrument-failed) · 1 unverified
calc_A_hat ppnp/pytorch/propagation.py ran MIT (permissive) · 0c74fb12dd5a5cd2 · report fixture: signature adj_matrix:csr_matrix/2/int · returned csr_matrix · level recorded 2026-09-25
calc_ppr_exact ppnp/pytorch/propagation.py ran MIT (permissive) · ae9d20a1aa16d8a2 · report fixture: signature adj_matrix:csr_matrix/2/float, alpha:float/0/float · returned ndarray · level recorded 2026-09-25
exclude_idx ppnp/preprocessing.py ran MIT (permissive) · 82bcc52c572684f5 · report fixture: signature idx:ndarray/1/int, idx_exclude_list:list/1/ndarray · returned ndarray · level recorded 2026-09-25
gen_seeds ppnp/preprocessing.py ran fingerprinted MIT (permissive) · 95c286604696f55a · report fixture: signature size:int/0/int · returned ndarray · level recorded 2026-09-25
get_dataloaders in 22 papers ppnp/pytorch/training.py ran MIT (permissive) · a75db933b77e116f · report fixture: signature idx:dict/0/?, labels_np:ndarray/1/int, batch_size:NoneType/0/? · returned dict · level recorded 2026-09-25
get_predictions in 17 papers ppnp/pytorch/training.py ran MIT (permissive) · 2d5ded2424bde021 · report fixture: signature model:callable/0/?, attr_matrix:Tensor/2/float, idx:Tensor/1/int, batch_size:int/0/int · returned ndarray · level recorded 2026-09-25
known_unknown_split ppnp/preprocessing.py ran MIT (permissive) · 7fd00eb2611bf53f · report fixture: signature idx:ndarray/1/int, nknown:int/0/int, seed:int/0/int · returned tuple · level recorded 2026-09-25
matrix_to_tensor ppnp/tensorflow/utils.py ran MIT (permissive) · 781c9e24c325cc7a · report fixture: signature X:ndarray/2/float · returned EagerTensor · level recorded 2026-09-25
matrix_to_torch ppnp/pytorch/utils.py ran MIT (permissive) · 8b5f84fdbffe3b4f · report fixture: signature X:ndarray/2/float · returned Tensor · level recorded 2026-09-25
sparse_dropout in 30 papers ppnp/tensorflow/utils.py ran MIT (permissive) · 3b270c601a03ed8c · report fixture: signature X:SparseTensor/2/float, keep_prob:float/0/float · returned SparseTensor · level recorded 2026-09-25
sparse_matrix_to_torch ppnp/pytorch/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 27f355e24ef27c9b · report fixture: signature X:csr_matrix/2/float · returned Tensor · level recorded 2026-09-22
sparse_matrix_to_tensor ppnp/tensorflow/utils.py unverified MIT (permissive) · 0a9edb272963d594 · report

Tasks

General ClassificationNode ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Chameleon (60%/20%/20% random splits) APPNP 1:1 Accuracy 51.91 ± 0.56 #35 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) APPNP 1:1 Accuracy 68.59 ± 0.30 #30 of 33 Archive leaderboard report
Node Classification Citeseer PPNP Accuracy 75.83% #16 of 71 Archive leaderboard report
Node Classification Citeseer PPNP Validation YES #16 of 71 Archive leaderboard report
Node Classification Citeseer APPNP Accuracy 75.73% #19 of 71 Archive leaderboard report
Node Classification Cora PPNP Accuracy 85.29% ± 0.25% #25 of 73 Archive leaderboard report
Node Classification Cora PPNP Validation YES #25 of 73 Archive leaderboard report
Node Classification Cora APPNP Accuracy 85.09% ± 0.25% #27 of 73 Archive leaderboard report
Node Classification Cora APPNP Validation YES #27 of 73 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) APPNP 1:1 Accuracy 79.41 ± 0.38 #30 of 33 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) APPNP 1:1 Accuracy 91.80 ± 0.63 #16 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) APPNP 1:1 Accuracy 38.86 ± 0.24 #22 of 37 Archive leaderboard report
Node Classification MS ACADEMIC APPNP Accuracy 93.27 ± 0.08 #1 of 3 Archive leaderboard report
Node Classification Penn94 APPNP Accuracy 74.33 ± 0.38 #26 of 32 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) APPNP 1:1 Accuracy 85.02 ± 0.09 #36 of 37 Archive leaderboard report
Node Classification Pubmed APPNP Accuracy 79.73 ± 0.31 #38 of 70 Archive leaderboard report
Node Classification Pubmed APPNP Validation YES #38 of 70 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) APPNP 1:1 Accuracy 34.77 ± 0.34 #34 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) APPNP 1:1 Accuracy 91.18 ± 0.70 #18 of 36 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) APPNP 1:1 Accuracy 92.00 ± 3.59 #17 of 35 Archive leaderboard report
Node Classification genius APPNP Accuracy 85.36 ± 0.62 #16 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) APPNP 1:1 Accuracy 51.91 ± 0.56 #29 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) APPNP 1:1 Accuracy 91.80 ± 0.63 #16 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe APPNP 1:1 Accuracy 67.21±0.56 #6 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 APPNP 1:1 Accuracy 74.33 ± 0.38 #22 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) APPNP 1:1 Accuracy 91.18 ± 0.70 #17 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) APPNP 1:1 Accuracy 92.00 ± 3.59 #17 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius APPNP 1:1 Accuracy 85.36 ± 0.62 #18 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers APPNP 1:1 Accuracy 60.97 ± 0.10 #22 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.

Methods

Introduced by this paper: APPNP

APPNPGraph Convolutional Networks

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