{"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/on-the-completeness-of-invariant-geometric","title":"On the Completeness of Invariant Geometric Deep Learning Models","arxiv_id":"2402.04836","date":"2024-02-07","proceeding":null,"authors":["Zian Li","Xiyuan Wang","Shijia Kang","Muhan Zhang"],"abstract":"Invariant models, one important class of geometric deep learning models, are capable of generating meaningful geometric representations by leveraging informative geometric features in point clouds. These models are characterized by their simplicity, good experimental results and computational efficiency. However, their theoretical expressive power still remains unclear, restricting a deeper understanding of the potential of such models. In this work, we concentrate on characterizing the theoretical expressiveness of a wide range of invariant models. We first rigorously bound the expressiveness of the most classic invariant model, message-passing neural networks incorporating distance (DisGNN), restricting its unidentifiable cases to be only highly symmetric point clouds. We then show that GeoNGNN, the geometric counterpart of one of the simplest subgraph graph neural networks (subgraph GNNs), can effectively break these corner cases' symmetry and thus achieve E(3)-completeness. By leveraging GeoNGNN as a theoretical tool, we further prove that: 1) most subgraph GNNs developed in traditional graph learning can be seamlessly extended to geometric scenarios with E(3)-completeness; 2) DimeNet, GemNet and SphereNet, three well-established invariant models, are also all capable of achieving E(3)-completeness. Our theoretical results fill the gap in the theoretical power of invariant models, contributing to a rigorous and comprehensive understanding of their capabilities. We also empirically evaluated GeoNGNN, the simplest model within the large E(3)-complete family we established, which achieves competitive results to models relying on high-order invariant/equivariant representations on molecule-relevant tasks.","url_abs":"https://arxiv.org/abs/2402.04836v2","url_pdf":"https://arxiv.org/pdf/2402.04836v2.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":"on-the-completeness-of-invariant-geometric","repo_url":"https://github.com/GraphPKU/GeoNGNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.04836","atlas_url":"https://app.syntology.ai/?focus=2402.04836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04836"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GraphPKU/GeoNGNN","reach":{"status":"ok"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"4caaef3d74e893f2","entry":"CR_E","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/CR_E.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/CR_E.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4caaef3d74e893f2"}},{"code_sha256_prefix":"656c90271465f47a","entry":"color_aggr","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/CR_E.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/CR_E.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"656c90271465f47a"}},{"code_sha256_prefix":"4022786a336867b9","entry":"color_reassignment","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/CR_E.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/CR_E.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4022786a336867b9"}},{"code_sha256_prefix":"e933658e0c41cf6f","entry":"get_all_policy","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/basic_utils.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/basic_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e933658e0c41cf6f"}},{"code_sha256_prefix":"bd7c6c6bce370aeb","entry":"get_complementary_policy","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/basic_utils.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/basic_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd7c6c6bce370aeb"}},{"code_sha256_prefix":"59a3739f7c137827","entry":"rmse","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"utils/loss_fns.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/utils/loss_fns.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59a3739f7c137827"}},{"code_sha256_prefix":"26ecb2d4a2734785","entry":"sample","repo":"GraphPKU/GeoNGNN","repo_kind":"official","path":"counterexamples/basic_utils.py","file_url":"https://github.com/GraphPKU/GeoNGNN/blob/HEAD/counterexamples/basic_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26ecb2d4a2734785"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}