Papers › PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

20 Jul 2020ICML 2020 1arXiv:2007.10408archive 2025-07-28

Zhengyang Shen, Lingshen He, Zhouchen Lin, Jinwen Ma

Recent research has shown that incorporating equivariance into neural network architectures is very helpful, and there have been some works investigating the equivariance of networks under group actions. However, as digital images and feature maps are on the discrete meshgrid, corresponding equivariance-preserving transformation groups are very limited. In this work, we deal with this issue from the connection between convolutions and partial differential operators (PDOs). In theory, assuming inputs to be smooth, we transform PDOs and propose a system which is equivariant to a much more general continuous group, the n-dimension Euclidean group. In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs). Theoretically, the approximation error of PDO-eConvs is of the quadratic order. It is the first time that the error analysis is provided when the equivariance is approximate. Extensive experiments on rotated MNIST and natural image classification show that PDO-eConvs perform competitively yet use parameters much more efficiently. Particularly, compared with Wide ResNets, our methods result in better results using only 12.6% parameters.

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 7 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (1 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.

shenzy08/PDO-eConvs officialmentioned on GitHubtfMITSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
ejnnr/steerable_pdo_experiments mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Roderickzzc/Pdo-econv-pytorch pytorchMITSyntology: 2 samples, 1 ran (0 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.

Code Syntology ran Syntology

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

2ran
5unverified

Licence: 0 of the 7 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.

shenzy08/PDO-eConvs official repository 5 samples, 1 ran (0 instrument-failed) · 4 unverified
get_coef in 8 papers cifar.py ran MIT (permissive) · 3153f50b8445e277 · report fixture: signature weight:EagerTensor/3/float, partial:ndarray/3/float · returned EagerTensor · level recorded 2026-09-25
open_conv2d cifar.py unverified MIT (permissive) · b9b3b78f58c55579 · report
open_conv2d mnist.py unverified MIT (permissive) · dd086cf5b7056f44 · report
subsample in 25 papers cifar.py unverified MIT (permissive) · ea673d7294c57b2c · report
z2_kernel mnist.py unverified MIT (permissive) · df1d3f2c0fe8b762 · report
Roderickzzc/Pdo-econv-pytorch community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_coef in 8 papers mwpdo_layers.py ran MIT (permissive) · 06968f8c3bffb773 · report fixture: signature weight:Tensor/3/float, num_inputs:int/0/int, num_outputs:int/0/int · returned Tensor · level recorded 2026-09-24
z2_kernel mwpdo_layers.py unverified MIT (permissive) · 1885497fb2dacd6c · report

Tasks

Image ClassificationRotated MNISTimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 PDO-eConv (p8, 4.6M) Percentage correct 96.5 #109 of 265 Archive leaderboard report
Image Classification CIFAR-10 PDO-eConv (p8, 2.62M) Percentage correct 96.32 #117 of 265 Archive leaderboard report
Image Classification CIFAR-10 PDO-eConv (p6m,0.37M) Percentage correct 94.62 #152 of 265 Archive leaderboard report
Image Classification CIFAR-10 PDO-eConv (p6,0.36M) Percentage correct 94.35 #159 of 265 Archive leaderboard report
Image Classification CIFAR-100 PDO-eConv (p8, 4.6M) Percentage correct 81.6 #117 of 211 Archive leaderboard report
Image Classification CIFAR-100 PDO-eConv (p8, 2.62M) Percentage correct 79.99 #133 of 211 Archive leaderboard report
Image Classification CIFAR-100 PDO-eConv (p6m,0.37M) Percentage correct 73 #163 of 211 Archive leaderboard report
Image Classification CIFAR-100 PDO-eConv (p6,0.36M) Percentage correct 72.87 #165 of 211 Archive leaderboard report
Image Classification MNIST-rot-12 PDO-eConv (ours) Test Error 1.87 #1 of 1 Archive leaderboard report
Image Classification MNIST-rot-12k (DA) PDO-eConv (ours) Test Error 0.709 #1 of 1 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