Papers › Provably Powerful Graph Networks

Provably Powerful Graph Networks

27 May 2019NeurIPS 2019 12arXiv:1905.11136archive 2025-07-28

Haggai Maron, Heli Ben-Hamu, Hadar Serviansky, Yaron Lipman

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressive power of graph neural networks (GNN). It was shown that the popular message passing GNN cannot distinguish between graphs that are indistinguishable by the 1-WL test (Morris et al. 2018; Xu et al. 2019). Unfortunately, many simple instances of graphs are indistinguishable by the 1-WL test. In search for more expressive graph learning models we build upon the recent k-order invariant and equivariant graph neural networks (Maron et al. 2019a,b) and present two results: First, we show that such k-order networks can distinguish between non-isomorphic graphs as good as the k-WL tests, which are provably stronger than the 1-WL test for k>2. This makes these models strictly stronger than message passing models. Unfortunately, the higher expressiveness of these models comes with a computational cost of processing high order tensors. Second, setting our goal at building a provably stronger, simple and scalable model we show that a reduced 2-order network containing just scaled identity operator, augmented with a single quadratic operation (matrix multiplication) has a provable 3-WL expressive power. Differently put, we suggest a simple model that interleaves applications of standard Multilayer-Perceptron (MLP) applied to the feature dimension and matrix multiplication. We validate this model by presenting state of the art results on popular graph classification and regression tasks. To the best of our knowledge, this is the first practical invariant/equivariant model with guaranteed 3-WL expressiveness, strictly stronger than message passing models.

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 8 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 8 samples from 2 repositories, 4 ran (4 with no instrument failure; 0 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.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hadarser/ProvablyPowerfulGraphNetworks mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
hadarser/ProvablyPowerfulGraphNetworks_torch mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified 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

8 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 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.

4ran
4unverified

Licence: 0 of the 8 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

hadarser/ProvablyPowerfulGraphNetworks community (archive-listed) 1 sample, 0 ran · 1 unverified
download_url in 32 papers utils/get_data.py unverified Apache-2.0 (permissive) · 7838e53265948514 · report
hadarser/ProvablyPowerfulGraphNetworks_torch community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
create_dirs in 6 papers utils/dirs.py ran Apache-2.0 (permissive) · dbb32e482cdfa29f · report fixture: signature dirs:list/1/str · returned int · level recorded 2026-09-25
diag_offdiag_maxpool in 5 papers layers/layers.py ran fingerprinted Apache-2.0 (permissive) · 15bb4b29cca9b4a1 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-25
get_config_from_json in 6 papers utils/config.py ran Apache-2.0 (permissive) · bbc60ae90dd59aa6 · report fixture: signature json_file:str/0/str · returned EasyDict · level recorded 2026-09-24
process_config in 13 papers utils/config.py ran Apache-2.0 (permissive) · a5ee96b6f2c405a2 · report fixture: signature json_file:str/0/str, dataset_name:str/0/str · returned EasyDict · level recorded 2026-09-24
load_dataset in 276 papers data_loader/data_helper.py unverified Apache-2.0 (permissive) · 9f1e79aa60bf79b8 · report
load_qm9 data_loader/data_helper.py unverified Apache-2.0 (permissive) · 5ffb58ac4245a0f8 · report
load_qm9_aux data_loader/data_helper.py unverified Apache-2.0 (permissive) · 6b4ad4ea61b1611e · report

Tasks

Graph ClassificationGraph LearningGraph Regression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification COLLAB PPGN Accuracy 81.38% #6 of 39 Archive leaderboard report
Graph Classification IMDb-B PPGN Accuracy 72.6% #39 of 51 Archive leaderboard report
Graph Classification IMDb-M PPGN Accuracy 50% #25 of 36 Archive leaderboard report
Graph Classification MUTAG PPGN Accuracy 90.55% #19 of 74 Archive leaderboard report
Graph Classification NCI1 PPGN Accuracy 83.19% #28 of 69 Archive leaderboard report
Graph Classification NCI109 PPGN Accuracy 82.23 #17 of 38 Archive leaderboard report
Graph Classification PROTEINS PPGN Accuracy 77.20% #34 of 103 Archive leaderboard report
Graph Classification PTC PPGN Accuracy 66.17% #20 of 37 Archive leaderboard report
Graph Regression ZINC-500k 3WLGNN MAE 0.303 #32 of 36 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