Papers › Directional Graph Networks

Directional Graph Networks

6 Oct 2020arXiv:2010.02863archive 2025-07-28

Dominique Beaini, Saro Passaro, Vincent Létourneau, William L. Hamilton, Gabriele Corso, Pietro Liò

The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this limitation, we propose the first globally consistent anisotropic kernels for GNNs, allowing for graph convolutions that are defined according to topologicaly-derived directional flows. First, by defining a vector field in the graph, we develop a method of applying directional derivatives and smoothing by projecting node-specific messages into the field. Then, we propose the use of the Laplacian eigenvectors as such vector field. We show that the method generalizes CNNs on an n-dimensional grid and is provably more discriminative than standard GNNs regarding the Weisfeiler-Lehman 1-WL test. We evaluate our method on different standard benchmarks and see a relative error reduction of 8% on the CIFAR10 graph dataset and 11% to 32% on the molecular ZINC dataset, and a relative increase in precision of 1.6% on the MolPCBA dataset. An important outcome of this work is that it enables graph networks to embed directions in an unsupervised way, thus allowing a better representation of the anisotropic features in different physical or biological problems.

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

No sample from the archive's official repository (Saro00/DGN) is linked to this paper; the 14 samples below come from 1 community repository. Syntology harvested code from Saro00/DGN for another paper.

Saro00/DGN: Syntology's graph links these samples to Principal Neighbourhood Aggregation for Graph Nets (arXiv:2004.05718; that paper's own run record: 33 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 22 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method.

Syntology 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 1 repository, 13 ran (11 with no instrument failure; 2 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 1 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. 1 of the 13 samples that ran has no recorded date.

Saro00/DGN officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Principal Neighbourhood Aggregation for Graph Nets (arXiv:2004.05718; that paper's own run record: 33 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 22 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
gbouritsas/gsn mentioned on GitHubpytorchMITSyntology: 14 samples, 13 ran (2 instrument-failed) · 1 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.

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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 2 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.

3ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
7ran
1unverified

Licence: 5 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, 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 gbouritsas/gsn. “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.

gbouritsas/gsn community (archive-listed) 14 samples, 13 ran (2 instrument-failed) · 1 unverified
aggregate_max in 5 papers directional_gsn/nets/aggregators.py ran fingerprinted MIT (permissive) · ee86c81b47055403 · report fixture: signature h:Tensor/2/float, vector_field:Tensor/2/float, h_in:Tensor/2/float · returned Tensor · level recorded 2026-09-24
aggregate_mean in 9 papers directional_gsn/nets/aggregators.py ran fingerprinted MIT (permissive) · 24fa352e05630952 · report fixture: signature h:Tensor/2/float, vector_field:Tensor/2/float, h_in:Tensor/2/float · returned Tensor · level recorded 2026-09-24
aggregate_min in 5 papers directional_gsn/nets/aggregators.py ran MIT (permissive) · a79bba4bc6411d00 · report fixture: signature h:Tensor/3/float, vector_field:Tensor/2/float, h_in:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_activation in 218 papers directional_gsn/nets/layers.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fe76e55f0b804b7b · report fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-22
get_custom_edge_list directional_gsn/utils_subgraph_encoding.py ran MIT (permissive) · 8c86e6abd3cdd4c4 · report fixture: signature ks:list/1/int, substructure_type:str/0/str, filename:NoneType/0/? · returned list · level recorded 2026-09-24
gpu_setup in 13 papers directional_gsn/main_HIV.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · f72434c0dcd5d11b · report fixture: signature use_gpu:bool/0/bool, gpu_id:int/0/int · returned device · level recorded 2026-09-22
scale_amplification directional_gsn/nets/scalers.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 5d07dbe669b9f73a · report fixture: signature h:float/0/float, D:int/0/int, avg_d:dict/0/? · returned float64 · level recorded 2026-09-22
scale_attenuation directional_gsn/nets/scalers.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · d0d453f04b18e8f1 · report fixture: signature h:float/0/float, D:int/0/int, avg_d:dict/0/? · returned float64 · level recorded 2026-09-22
scale_identity directional_gsn/nets/scalers.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 2d32c33e16bad56e · report fixture: signature h:Tensor/2/float, D:NoneType/0/?, avg_d:NoneType/0/? · returned Tensor · level recorded 2026-09-22
str2ListOfLists2int directional_gsn/utils_parsing.py ran MIT (permissive) · 94c293b9defb4188 · report fixture: signature v:str/0/str · returned list · level recorded 2026-09-24
str2ListOfListsOfLists2int directional_gsn/utils_parsing.py ran MIT (permissive) · fa9cf77a40a3bfae · report fixture: signature v:str/0/str · returned list · level recorded 2026-09-24
str2bool in 533 papers directional_gsn/utils_parsing.py ran · violated contract MIT (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
to_undirected directional_gsn/utils_graph_processing.py ran MIT (permissive) · 77a61130d1c9fd6b · report fixture: signature edge_index:tuple/1/Tensor · returned Tensor · level recorded 2026-09-25
encode in 73 papers directional_gsn/utils_one_hot_encoding.py unverified MIT (permissive) · 831368bc983a71e0 · report

Tasks

Data AugmentationGraph ClassificationGraph RegressionNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification CIFAR10 100k DGN Accuracy (%) 72.84 #10 of 20 Archive leaderboard report
Graph Property Prediction ogbg-molhiv DGN Ext. data No #21 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv DGN Number of params 114065 #21 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv DGN Test ROC-AUC 0.7970 ± 0.0097 #21 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv DGN Validation ROC-AUC 0.8470 ± 0.0047 #21 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molpcba DGN Ext. data No #21 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba DGN Number of params 6732696 #21 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba DGN Test AP 0.2885 ± 0.0030 #21 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba DGN Validation AP 0.2970 ± 0.0021 #21 of 36 Archive leaderboard report
Node Classification PATTERN 100k DGN Accuracy (%) 86.680 #2 of 9 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