Papers › Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products

Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products

18 Jan 2024arXiv:2401.10216archive 2025-07-28

Shengjie Luo, Tianlang Chen, Aditi S. Krishnapriyan

Developing equivariant neural networks for the E(3) group plays an important role in modeling 3D data across real-world applications. Enforcing this equivariance primarily involves the tensor products of irreducible representations (irreps). However, the computational complexity of such operations increases significantly as higher-order tensors are used. In this work, we propose a systematic approach to substantially accelerate the computation of the tensor products of irreps. We mathematically connect the commonly used Clebsch-Gordan coefficients to the Gaunt coefficients, which are integrals of products of three spherical harmonics. Through Gaunt coefficients, the tensor product of irreps becomes equivalent to the multiplication between spherical functions represented by spherical harmonics. This perspective further allows us to change the basis for the equivariant operations from spherical harmonics to a 2D Fourier basis. Consequently, the multiplication between spherical functions represented by a 2D Fourier basis can be efficiently computed via the convolution theorem and Fast Fourier Transforms. This transformation reduces the complexity of full tensor products of irreps from 𝒪(L⁶) to 𝒪(L³), where L is the max degree of irreps. Leveraging this approach, we introduce the Gaunt Tensor Product, which serves as a new method to construct efficient equivariant operations across different model architectures. Our experiments on the Open Catalyst Project and 3BPA datasets demonstrate both the increased efficiency and improved performance of our approach.

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 24 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 6 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 4 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: 23 samples from 1 repository, 19 ran (12 with no instrument failure; 7 where Syntology's instrument failed); community: 1 sample 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 20 samples that ran has no recorded date.

lsj2408/gaunt-tensor-product officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 23 samples, 19 ran (7 instrument-failed) · 4 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

24 samples harvested: 20 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 6 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 4 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 · honoured contract
6ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
6ran
4unverified

Licence: 2 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 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.

lsj2408/gaunt-tensor-product official repository 23 samples, 19 ran (7 instrument-failed) · 4 unverified
ClebschGordan force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran Apache-2.0 (permissive) · a0b88a548830cf98 · report fixture: returned ClebschGordan · level recorded 2026-09-22
FFT efficiency-comparison/fft.py ran Apache-2.0 (permissive) · 05fbb48f432304eb · report fixture: signature fourier_coef1:Tensor/2/complex, fourier_coef2:Tensor/2/complex, return_real:bool/0/bool · returned Tensor · level recorded 2026-09-24
FFT_batch_channel efficiency-comparison/fft.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ce1ffb6956fa7c7b · report fixture: signature fourier_coef1:Tensor/4/complex, fourier_coef2:Tensor/4/complex, return_real:bool/0/bool · returned Tensor · level recorded 2026-09-24
FFT_channel efficiency-comparison/fft.py ran Apache-2.0 (permissive) · f18e28a7c0cf9e04 · report fixture: signature fourier_coef1:Tensor/3/complex, fourier_coef2:Tensor/3/complex, return_real:bool/0/bool · returned Tensor · level recorded 2026-09-24
Rot3DCoeffs force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran Apache-2.0 (permissive) · 5a51dad6fe773f9c · report fixture: returned Rot3DCoeffs · level recorded 2026-09-22
cg_conditions force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran · violated contract fingerprinted Apache-2.0 (permissive) · e8488725c2821c4e · report fixture: signature j1:int/0/int, m1:int/0/int, j2:int/0/int, m2:int/0/int, J:int/0/int, M:int/0/int · returned bool · level recorded 2026-09-22
cg_l_condition force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran · violated contract Apache-2.0 (permissive) · 1d1c344056d67391 · report fixture: signature j1:int/0/int, j2:int/0/int, J:int/0/int · returned bool · level recorded 2026-09-22
cg_m_condition force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran · violated contract fingerprinted Apache-2.0 (permissive) · c6a6415c93989edb · report fixture: signature m1:Tensor/1/float, m2:Tensor/1/float, M:Tensor/1/float · returned Tensor · level recorded 2026-09-22
clebschgordan force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2ceb0025f1a3db12 · report fixture: signature j1:int/0/int, m1:int/0/int, j2:int/0/int, m2:int/0/int, J:int/0/int, M:int/0/int · returned float · level recorded 2026-09-22
coco_filter force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran Apache-2.0 (permissive) · ad67339b74a878f4 · report fixture: signature ll:list/1/int, mm:list/1/int, invariant:bool/0/bool · returned bool · level recorded 2026-09-24
coco_filter2 force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot.py ran Apache-2.0 (permissive) · 629660a18e55d63e · report fixture: signature ll:list/1/int, mm:list/1/int, kk:list/1/int, invariant:bool/0/bool · returned bool · level recorded 2026-09-24
create_Jx force-field-modeling-3bpa/MACE/LieCG/Lie_groups/Rotations.py ran · violated contract Apache-2.0 (permissive) · 662f5627f0873e13 · report fixture: signature j:int/0/int · returned Tensor · level recorded 2026-09-24
create_Jy force-field-modeling-3bpa/MACE/LieCG/Lie_groups/Rotations.py ran · violated contract Apache-2.0 (permissive) · 67bb14caad016db4 · report fixture: signature j:int/0/int · returned Tensor · level recorded 2026-09-24
f2sh efficiency-comparison/f2sh.py ran · our draft was wrong Apache-2.0 (permissive) · 74dca1841d91deed · report fixture: signature fourier_coef:Tensor/2/float, f2sh_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
f2sh_batch_channel efficiency-comparison/f2sh.py ran · our draft was wrong Apache-2.0 (permissive) · 055b503cdc6b0c1b · report fixture: signature fourier_coef:Tensor/4/float, f2sh_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
f2sh_channel efficiency-comparison/f2sh.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8c4389223f782822 · report fixture: signature fourier_coef:Tensor/3/float, f2sh_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
sh2f efficiency-comparison/sh2f.py ran · our draft was wrong Apache-2.0 (permissive) · 27dc61986a394a2a · report fixture: signature sh_coeff:Tensor/2/float, sh2f_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
sh2f_batch_channel efficiency-comparison/sh2f.py ran · our draft was wrong Apache-2.0 (permissive) · 31a695005a03793b · report fixture: signature sh_coeff:Tensor/4/float, sh2f_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
sh2f_channel efficiency-comparison/sh2f.py ran · our draft was wrong Apache-2.0 (permissive) · d382cba70545c430 · report fixture: signature sh_coeff:Tensor/3/float, sh2f_bases:Tensor/4/float · returned Tensor · level recorded 2026-09-24
U_matrix_real force-field-modeling-3bpa/MACE/LieCG/CG_coefficients/CG_rot_real.py unverified Apache-2.0 (permissive) · cee2ed5ee0d679ee · report
create_J force-field-modeling-3bpa/MACE/LieCG/Lie_groups/Rotations.py unverified Apache-2.0 (permissive) · ae70e599fd8a7ff6 · report
linear_out_irreps force-field-modeling-3bpa/MACE/MACE/modules/irreps_tools.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 3ded1daa0770bc97 · report
tp_out_irreps_with_instructions force-field-modeling-3bpa/MACE/MACE/modules/irreps_tools.py unverified Apache-2.0 (permissive) · 18d9a7b0f17155e6 · report
e3nn/e3nn community 1 sample, 1 ran (0 instrument-failed) · 0 unverified
t_or_f examples/tensor_product_benchmark.py ran · violated contract licence not identified · pointer only · 440a098dda4f24f0 · report fixture: signature arg:str/0/str · returned bool · level recorded, date not recorded

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Gaunt Tensor Product (graph method: Gaunt Tensor Product). 6 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 3 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. Rot3DCoeffs entry · level 1 · ran · 5a51dad6fe773f9c
  2. ClebschGordan helper · level 1 · ran · a0b88a548830cf98
  3. cg_conditions helper · level 1 · ran · violated contract · e8488725c2821c4e
  4. clebschgordan helper · level 1 · ran · honoured contract · 2ceb0025f1a3db12
  5. cg_l_condition helper · level 1 · ran · violated contract · 1d1c344056d67391
  6. cg_m_condition helper · level 1 · ran · violated contract · c6a6415c93989edb

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="2401.10216") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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