Papers › Approximately Equivariant Graph Networks

Approximately Equivariant Graph Networks

21 Aug 2023NeurIPS 2023 11arXiv:2308.10436archive 2025-07-28

Ningyuan Huang, Ron Levie, Soledad Villar

Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean convolution neural networks (CNNs). However, these two symmetries are fundamentally different: The translation equivariance of CNNs corresponds to symmetries of the fixed domain acting on the image signals (sometimes known as active symmetries), whereas in GNNs any permutation acts on both the graph signals and the graph domain (sometimes described as passive symmetries). In this work, we focus on the active symmetries of GNNs, by considering a learning setting where signals are supported on a fixed graph. In this case, the natural symmetries of GNNs are the automorphisms of the graph. Since real-world graphs tend to be asymmetric, we relax the notion of symmetries by formalizing approximate symmetries via graph coarsening. We present a bias-variance formula that quantifies the tradeoff between the loss in expressivity and the gain in the regularity of the learned estimator, depending on the chosen symmetry group. To illustrate our approach, we conduct extensive experiments on image inpainting, traffic flow prediction, and human pose estimation with different choices of symmetries. We show theoretically and empirically that the best generalization performance can be achieved by choosing a suitably larger group than the graph automorphism, but smaller than the permutation group.

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 14 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 9 ran (2 with no instrument failure; 7 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nhuang37/approx_equivariant_graph_nets officialmentioned in paperpytorchSyntology: 14 samples, 9 ran (7 instrument-failed) · 5 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

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
1ran
5unverified

Licence: 14 of the 14 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 nhuang37/approx_equivariant_graph_nets. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

nhuang37/approx_equivariant_graph_nets official repository 14 samples, 9 ran (7 instrument-failed) · 5 unverified
adj_mx_from_edges in 5 papers Human_Pose_Est/common/graph_utils.py ran · our draft was wrong no licence file found · pointer only · 267c4a7846f1eab2 · report fixture: signature num_pts:int/0/int, edges:list/1/list, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-22
calculate_normalized_laplacian in 11 papers DCRNN_Pytorch/lib/utils.py ran · our draft was wrong no licence file found · pointer only · e7b2e6a60daa42ca · report fixture: signature adj:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
calculate_random_walk_matrix in 5 papers DCRNN_Pytorch/lib/utils.py ran · our draft was wrong no licence file found · pointer only · 3beffe79b677036e · report fixture: signature adj_mx:ndarray/2/float · returned coo_matrix · level recorded 2026-09-24
calculate_reverse_random_walk_matrix DCRNN_Pytorch/lib/utils.py ran · our draft was wrong no licence file found · pointer only · 56ec469b6198b701 · report fixture: signature adj_mx:ndarray/2/float · returned coo_matrix · level recorded 2026-09-24
indexer Human_Pose_Est/models/sem_graph_conv_autG.py ran no licence file found · pointer only · 4f0ac7ede58734c3 · report fixture: signature n:int/0/int, d:int/0/int, blocks:list/1/int · returned list · level recorded 2026-09-24
mpjpe in 13 papers Human_Pose_Est/common/loss.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3afb541a8147d123 · report fixture: signature predicted:Tensor/3/float, target:Tensor/3/float · returned Tensor · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
Human_Pose_Est/common/graph_utils.py ran · violated contract no licence file found · pointer only · aa9c29936dee40a7 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
p_mpjpe in 6 papers Human_Pose_Est/common/loss.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 29d56deadc8fcd3c · report fixture: signature predicted:ndarray/3/float, target:ndarray/3/float · returned float32 · level recorded 2026-09-24
sparse_mx_to_torch_sparse_tensor in 41 papers Human_Pose_Est/common/graph_utils.py ran · our draft was wrong no licence file found · pointer only · bdc1f1dad6d978e7 · report fixture: signature sparse_mx:coo_matrix/2/float · returned Tensor · level recorded 2026-09-22
generate_graph_seq2seq_io_data in 10 papers DCRNN_Pytorch/generate_training_data_t3.py unverified no licence file found · pointer only · fde1716c2510a3a6 · report
masked_mae_tf DCRNN_Pytorch/lib/metrics.py unverified no licence file found · pointer only · 73560f28f2daab27 · report
masked_mse_tf DCRNN_Pytorch/lib/metrics.py unverified no licence file found · pointer only · 22a732ec40427724 · report
masked_rmse_tf DCRNN_Pytorch/lib/metrics.py unverified no licence file found · pointer only · d6da0ac5290c5a57 · report
weighted_mpjpe in 7 papers Human_Pose_Est/common/loss.py unverified no licence file found · pointer only · 6dd3ba892d9349d8 · report

Tasks

Image InpaintingPose EstimationTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionFocus

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