{"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/deconstructing-equivariant-representations-in","title":"Deconstructing equivariant representations in molecular systems","arxiv_id":"2410.08131","date":"2024-10-10","proceeding":null,"authors":["Kin Long Kelvin Lee","Mikhail Galkin","Santiago Miret"],"abstract":"Recent equivariant models have shown significant progress in not just chemical property prediction, but as surrogates for dynamical simulations of molecules and materials. Many of the top performing models in this category are built within the framework of tensor products, which preserves equivariance by restricting interactions and transformations to those that are allowed by symmetry selection rules. Despite being a core part of the modeling process, there has not yet been much attention into understanding what information persists in these equivariant representations, and their general behavior outside of benchmark metrics. In this work, we report on a set of experiments using a simple equivariant graph convolution model on the QM9 dataset, focusing on correlating quantitative performance with the resulting molecular graph embeddings. Our key finding is that, for a scalar prediction task, many of the irreducible representations are simply ignored during training -- specifically those pertaining to vector ($l=1$) and tensor quantities ($l=2$) -- an issue that does not necessarily make itself evident in the test metric. We empirically show that removing some unused orders of spherical harmonics improves model performance, correlating with improved latent space structure. We provide a number of recommendations for future experiments to try and improve efficiency and utilization of equivariant features based on these observations.","url_abs":"https://arxiv.org/abs/2410.08131v1","url_pdf":"https://arxiv.org/pdf/2410.08131v1.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":[{"paper_slug":"deconstructing-equivariant-representations-in","repo_url":"https://github.com/IntelLabs/EquiTriton","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.08131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08131"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IntelLabs/EquiTriton","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"d6908997456703d6","entry":"benchmark","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/benchmark.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6908997456703d6"}},{"code_sha256_prefix":"c45167a425d70a1f","entry":"calculate_lastdim_num_blocks","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/utils.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c45167a425d70a1f"}},{"code_sha256_prefix":"cf2583413462f7f6","entry":"make_output_tensor","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/sph_harm/bindings.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/sph_harm/bindings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2583413462f7f6"}},{"code_sha256_prefix":"8177197e118a29ab","entry":"num_irreps_projections","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/utils.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8177197e118a29ab"}},{"code_sha256_prefix":"f7ce9aca98450801","entry":"profile","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/benchmark.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7ce9aca98450801"}},{"code_sha256_prefix":"edaa405ed615c3f4","entry":"split_tensor_by_l","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/sph_harm/bindings.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/sph_harm/bindings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"edaa405ed615c3f4"}},{"code_sha256_prefix":"820b8ceee22abf19","entry":"torch_spherical_harmonic","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/sph_harm/direct/utils.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/sph_harm/direct/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"820b8ceee22abf19"}},{"code_sha256_prefix":"cb24ab74855570a9","entry":"total_projections","repo":"IntelLabs/EquiTriton","repo_kind":"official","path":"src/equitriton/sph_harm/bindings.py","file_url":"https://github.com/IntelLabs/EquiTriton/blob/HEAD/src/equitriton/sph_harm/bindings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb24ab74855570a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}