{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/symdiff-equivariant-diffusion-via-stochastic","title":"SymDiff: Equivariant Diffusion via Stochastic Symmetrisation","arxiv_id":"2410.06262","date":"2024-10-08","proceeding":null,"authors":["Leo Zhang","Kianoosh Ashouritaklimi","Yee Whye Teh","Rob Cornish"],"abstract":"We propose SymDiff, a novel method for constructing equivariant diffusion models using the recently introduced framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is deployed at sampling time, and is lightweight, computationally efficient, and easy to implement on top of arbitrary off-the-shelf models. Notably, in contrast to previous work, SymDiff typically does not require any neural network components that are intrinsically equivariant, avoiding the need for complex parameterizations and the use of higher-order geometric features. Instead, our method can leverage highly scalable modern architectures as drop-in replacements for these more constrained alternatives. We show that this additional flexibility yields significant empirical benefit on $\\mathrm{E}(3)$-equivariant molecular generation. To the best of our knowledge, this is the first application of symmetrisation to generative modelling, suggesting its potential in this domain more generally.","url_abs":"https://arxiv.org/abs/2410.06262v1","url_pdf":"https://arxiv.org/pdf/2410.06262v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.06262","atlas_url":"https://app.syntology.ai/?focus=2410.06262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06262"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/DiT","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/leozhangML/SymDiff","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":12,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4ed06d5114046b7e","entry":"compute_loss_and_nll","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"qm9/losses.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/qm9/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ed06d5114046b7e"}},{"code_sha256_prefix":"1b43a8d3512fffdf","entry":"compute_n_nodes_dict","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"analyse_geom.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/analyse_geom.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b43a8d3512fffdf"}},{"code_sha256_prefix":"12f8e6ced3e7acc4","entry":"convert_str_to_bool","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"eval_analyze.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/eval_analyze.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12f8e6ced3e7acc4"}},{"code_sha256_prefix":"85c8c5cc8774ca97","entry":"get_optim","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"qm9/models.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/qm9/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85c8c5cc8774ca97"}},{"code_sha256_prefix":"0f0e2214104b64a1","entry":"get_scheduler","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"qm9/models.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/qm9/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0e2214104b64a1"}},{"code_sha256_prefix":"abeabf4526a83aaa","entry":"gradient_clipping","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abeabf4526a83aaa"}},{"code_sha256_prefix":"3858d40af29fc810","entry":"load_split_data","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"build_geom_dataset.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/build_geom_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3858d40af29fc810"}},{"code_sha256_prefix":"e372872a463628a7","entry":"random_rotation","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e372872a463628a7"}},{"code_sha256_prefix":"90c529ca8e85d3db","entry":"sum_except_batch","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"qm9/losses.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/qm9/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"code_sha256_prefix":"f576c0a0e0ae29c2","entry":"get_args_gen","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"eval_conditional_qm9.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/eval_conditional_qm9.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f576c0a0e0ae29c2"}},{"code_sha256_prefix":"476ddad204b6b1b3","entry":"get_dataset_info","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"configs/datasets_config.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/configs/datasets_config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"476ddad204b6b1b3"}},{"code_sha256_prefix":"fc4da23dd75dcb46","entry":"load_model","repo":"leozhangML/SymDiff","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc4da23dd75dcb46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}