Papers › EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

21 Jun 2023arXiv:2306.12059archive 2025-07-28

Yi-Lun Liao, Brandon Wood, Abhishek Das, Tess Smidt

Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems. However, they are limited to small degrees of equivariant representations due to their computational complexity. In this paper, we investigate whether these architectures can scale well to higher degrees. Starting from Equiformer, we first replace SO(3) convolutions with eSCN convolutions to efficiently incorporate higher-degree tensors. Then, to better leverage the power of higher degrees, we propose three architectural improvements -- attention re-normalization, separable S² activation and separable layer normalization. Putting this all together, we propose EquiformerV2, which outperforms previous state-of-the-art methods on large-scale OC20 dataset by up to 9% on forces, 4% on energies, offers better speed-accuracy trade-offs, and 2× reduction in DFT calculations needed for computing adsorption energies. Additionally, EquiformerV2 trained on only OC22 dataset outperforms GemNet-OC trained on both OC20 and OC22 datasets, achieving much better data efficiency. Finally, we compare EquiformerV2 with Equiformer on QM9 and OC20 S2EF-2M datasets to better understand the performance gain brought by higher degrees.

PaperPDFCodeCode 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="2306.12059")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · fixture could not drive it.

By repository: official repository: 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

atomicarchitects/equiformer_v2 officialmentioned in papermentioned on GitHubpytorchMIT report
atomicarchitects/dens mentioned 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

5 samples harvested; 3 ran; 1 honoured the contract we drafted; 2 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.

1ran · honoured contract
1ran · violated contract
1ran · fixture could not drive it
2unverified

Licence: 0 of the 5 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 atomicarchitects/equiformer_v2. “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.

drop_path atomicarchitects/equiformer_v2/nets/equiformer_v2/drop.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3ac6b7d76e8e3584 · report
gaussian atomicarchitects/equiformer_v2/nets/equiformer_v2/gaussian_rbf.py official repository ran · violated contract MIT (permissive) · 294ba20b052bfbc7 · report
get_l_to_all_m_expand_index atomicarchitects/equiformer_v2/nets/equiformer_v2/layer_norm.py official repository ran · honoured contract fingerprinted MIT (permissive) · d4c1ba3933fbb7ac · report
get_normalization_layer atomicarchitects/equiformer_v2/nets/equiformer_v2/layer_norm.py official repository unverified MIT (permissive) · f58e462fb9c75bb8 · report
init_edge_rot_mat atomicarchitects/equiformer_v2/nets/equiformer_v2/edge_rot_mat.py official repository unverified MIT (permissive) · b316bf7a13f27e97 · report

Tasks

Graph Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction QM9 EquiformerV2 Standardized MAE 0.67 #4 of 10 Archive leaderboard report
Graph Property Prediction QM9 EquiformerV2 alpha (ma) 47 #4 of 10 Archive leaderboard report
Graph Property Prediction QM9 EquiformerV2 gap (meV) 29 #4 of 10 Archive leaderboard report
Graph Property Prediction QM9 EquiformerV2 logMAE -5.87 #4 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