Papers › E(n) Equivariant Graph Neural Networks

E(n) Equivariant Graph Neural Networks

19 Feb 2021arXiv:2102.09844archive 2025-07-28

Victor Garcia Satorras, Emiel Hoogeboom, Max Welling

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.

PaperPDFCodeCode Syntology ranMethod as code

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 15 code samples harvested from 4 repositories linked to this paper: 15 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 14 samples from 3 repositories, 14 ran (9 with no instrument failure; 5 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vgsatorras/egnn officialmentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
gerkone/egnn-jax mentioned on GitHubjaxSyntology: not harvested report
lucidrains/egnn-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
oumarkaba/channels_egnn mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
stdereka/egnn mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (2 instrument-failed) · 0 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

15 samples harvested: 15 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 0 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 · honoured contract
4ran · our draft was wrong
2ran; the contract check could not run
8ran

Licence: 7 of the 15 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 4 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

vgsatorras/egnn official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
unsorted_segment_sum in 33 papers models/egnn_clean/egnn_clean.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 5fb62a78eb65d3d7 · report fixture: signature data:Tensor/2/float, segment_ids:Tensor/1/int, num_segments:int/0/int · returned Tensor · level recorded 2026-09-22
lucidrains/egnn-pytorch community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
CoorsNorm egnn_pytorch/egnn_pytorch.py ran fingerprinted MIT (permissive) · ffaef7e169a747f9 · report fixture: returned CoorsNorm · level recorded 2026-09-22
EGNN egnn_pytorch/egnn_pytorch.py ran MIT (permissive) · 417dea916987b70b · report fixture: returned EGNN · level recorded 2026-09-22
Swish_ egnn_pytorch/egnn_pytorch.py ran fingerprinted MIT (permissive) · bfa2a8ec7cf892d8 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
fourier_encode_dist egnn_pytorch/egnn_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 970eaf2b4e05bf0b · report fixture: signature x:Tensor/2/float, num_encodings:int/0/int, include_self:bool/0/bool · returned Tensor · level recorded 2026-09-22
safe_div in 29 papers egnn_pytorch/egnn_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · d92b80051870e976 · report fixture: signature num:Tensor/2/float, den:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
oumarkaba/channels_egnn community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
EGNN models/egnn_clean/egnn_clean.py ran · metamorphic tier: deterministic MIT (permissive) · 13bfce0047d020a5 · report fixture: returned EGNN · level recorded 2026-09-22
E_GCL in 5 papers models/egnn_clean/egnn_clean.py ran · metamorphic tier: deterministic MIT (permissive) · 1e061bf006a92838 · report fixture: returned E_GCL · level recorded 2026-09-22
unsorted_segment_mean in 27 papers models/egnn_clean/egnn_clean.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · bc66f19be57720e7 · report fixture: signature data:Tensor/2/float, segment_ids:Tensor/1/int, num_segments:int/0/int · returned Tensor · level recorded 2026-09-22
stdereka/egnn community (archive-listed) 6 samples, 6 ran (2 instrument-failed) · 0 unverified
EquivariantGNN src/egnn/model/gnn.py ran · metamorphic tier: deterministic no licence file found · pointer only · bc84667b27c8cd1c · report fixture: returned EquivariantGNN · level recorded 2026-09-22
EquivariantGraphConvolution src/egnn/model/gnn.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1c02f9fc1ecdc6a7 · report fixture: returned EquivariantGraphConvolution · level recorded 2026-09-22
ResidualMLP src/egnn/model/gnn.py ran · metamorphic tier: deterministic no licence file found · pointer only · 70eef633a4bb2e21 · report fixture: returned ResidualMLP · level recorded 2026-09-22
pack_node_params src/egnn/model/gnn.py ran · honoured contract fingerprinted no licence file found · pointer only · 63fe5b745690a4c5 · report fixture: signature coords:Tensor/2/float, velocities:Tensor/2/float, properties:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unpack_node_params src/egnn/model/gnn.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · f94b0bdff7e41ab4 · report fixture: signature node_params:Tensor/2/float, num_coords:int/0/int, num_velocities:int/0/int · returned tuple · level recorded 2026-09-22
unsorted_segment_sum in 33 papers src/egnn/model/gnn.py ran · our draft was wrong no licence file found · pointer only · 90bd74d59afb1975 · report fixture: signature data:Tensor/2/float, segment_ids:Tensor/1/int, num_segments:int/0/int · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for E(n)-Equivariant Graph Neural Networks (EGNNs) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for E(n)-Equivariant Graph Neural Networks (EGNNs) (graph method: E(n)-Equivariant Graph Neural Networks (EGNNs)). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. EGNN entry · level 1 · ran · 13bfce0047d020a5
  2. E_GCL model · level 1 · ran · 1e061bf006a92838
  3. unsorted_segment_mean helper · level 1 · ran; the contract check could not run (RAISES) · bc66f19be57720e7
  4. unsorted_segment_sum helper · level 1 · ran · our draft was wrong · 5fb62a78eb65d3d7

harvested Assembly for E(n)-Equivariant Graph Neural Networks (EGNNs) (graph method: E(n)-Equivariant Graph Neural Networks (EGNNs)). 7 bricks; individually on a fixture: 7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. EquivariantGNN entry · level 1 · ran · bc84667b27c8cd1c
  2. EquivariantGraphConvolution model · level 1 · ran · 1c02f9fc1ecdc6a7
  3. ResidualMLP helper · level 1 · ran · 70eef633a4bb2e21
  4. pack_node_params helper · level 1 · ran · honoured contract · 63fe5b745690a4c5
  5. unpack_node_params helper · level 1 · ran; the contract check could not run (RAISES) · f94b0bdff7e41ab4
  6. unsorted_segment_mean helper · level 1 · ran; the contract check could not run (RAISES) · bc66f19be57720e7
  7. unsorted_segment_sum helper · level 1 · ran · our draft was wrong · 90bd74d59afb1975

harvested Assembly for E(n)-Equivariant Graph Neural Networks (EGNNs) (graph method: E(n)-Equivariant Graph Neural Networks (EGNNs)). 7 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. EGNN entry · level 1 · ran · 417dea916987b70b
  2. CoorsNorm helper · level 1 · ran · ffaef7e169a747f9
  3. batched_index_select helper · level 1 · ran · our draft was wrong · 582b2f1aa69315a0
  4. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  5. fourier_encode_dist helper · level 1 · ran · our draft was wrong · 970eaf2b4e05bf0b
  6. safe_div helper · level 1 · ran · our draft was wrong · d92b80051870e976
  7. Swish_ helper · level 1 · ran · bfa2a8ec7cf892d8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2102.09844") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph Property PredictionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction QM9 EGNN Standardized MAE 1.23 #10 of 10 Archive leaderboard report
Graph Property Prediction QM9 EGNN alpha (ma) 71 #10 of 10 Archive leaderboard report
Graph Property Prediction QM9 EGNN gap (meV) 48 #10 of 10 Archive leaderboard report
Graph Property Prediction QM9 EGNN logMAE -5.43 #10 of 10 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