Papers › Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

5 Jun 2023NeurIPS 2023 11arXiv:2306.02866archive 2025-07-28

Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade, Hyeokjun An, Seunghoon Hong

We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and symmetrize it to be equivariant to the given group by employing a small equivariant network that parameterizes the probabilistic distribution underlying the symmetrization. The distribution is end-to-end trained with the base model which can maximize performance while reducing sample complexity of symmetrization. We show that this approach ensures not only equivariance to given group but also universal approximation capability in expectation. We implement our method on various base models, including patch-based transformers that can be initialized from pretrained vision transformers, and test them for a wide range of symmetry groups including permutation and Euclidean groups and their combinations. Empirical tests show competitive results against tailored equivariant architectures, suggesting the potential for learning equivariant functions for diverse groups using a non-equivariant universal base architecture. We further show evidence of enhanced learning in symmetric modalities, like graphs, when pretrained from non-symmetric modalities, like vision. Code is available at https://github.com/jw9730/lps.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.02866")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jw9730/lps officialmentioned in papermentioned on GitHubpytorchMIT 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

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13unverified

Licence: 0 of the 13 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 jw9730/lps. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

configure_experiment jw9730/lps/src/train/configure_experiment.py official repository unverified MIT (permissive) · 30ecf9c4638e103d · report
is_order_zero_rep jw9730/lps/src/symmetry/symmetry.py official repository unverified MIT (permissive) · 5ddcff293e9e81dd · report
load_ckpt jw9730/lps/src/train/configure_model.py official repository unverified MIT (permissive) · aa0af576b7d7f97d · report
rep2str jw9730/lps/src/symmetry/symmetry.py official repository unverified MIT (permissive) · ad9fb8eddc7b89d4 · report
rep2str_prod jw9730/lps/src/symmetry/symmetry.py official repository unverified MIT (permissive) · b9dd162078065dcb · report
setup_1d jw9730/lps/src/symmetry/projections_conv.py official repository unverified MIT (permissive) · b44893b793a1fb27 · report
setup_1x1d jw9730/lps/src/symmetry/projections_conv.py official repository unverified MIT (permissive) · aeee381b7ce6889f · report
setup_2d jw9730/lps/src/symmetry/projections_conv.py official repository unverified MIT (permissive) · e2df87252356f197 · report
setup_backbone jw9730/lps/src/model/backbone.py official repository unverified MIT (permissive) · ea080e245b0108ac · report
setup_ckpt_path jw9730/lps/src/train/configure_model.py official repository unverified MIT (permissive) · 0ea80e71d0bbf2e7 · report
setup_data_directory jw9730/lps/src/train/configure_data.py official repository unverified MIT (permissive) · 37cd6d25bd489cd6 · report
setup_log_directory jw9730/lps/src/train/configure_experiment.py official repository unverified MIT (permissive) · ac084803f3c4b240 · report
setup_save_directory jw9730/lps/src/train/configure_experiment.py official repository unverified MIT (permissive) · b7a1d1b7e81f6f93 · report

Tasks

Graph ClassificationGraph RegressionLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification Peptides-func ViT-PS AP 0.6575 #28 of 44 Archive leaderboard report
Graph Regression Peptides-struct ViT-PS MAE 0.2559 #30 of 39 Archive leaderboard report
Link Prediction PCQM-Contact ViT-PS Hits@1 0.3287 #1 of 18 Archive leaderboard report
Link Prediction PCQM-Contact ViT-PS Hits@10 0.9526 #1 of 18 Archive leaderboard report
Link Prediction PCQM-Contact ViT-PS Hits@3 0.6694 #1 of 18 Archive leaderboard report
Link Prediction PCQM-Contact ViT-PS MRR 0.5341 #1 of 18 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.

Methods

BASE

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