{"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/expressive-sign-equivariant-networks-for-1","title":"Expressive Sign Equivariant Networks for Spectral Geometric Learning","arxiv_id":"2312.02339","date":"2023-12-04","proceeding":"NeurIPS 2023 11","authors":["Derek Lim","Joshua Robinson","Stefanie Jegelka","Haggai Maron"],"abstract":"Recent work has shown the utility of developing machine learning models that respect the structure and symmetries of eigenvectors. These works promote sign invariance, since for any eigenvector v the negation -v is also an eigenvector. However, we show that sign invariance is theoretically limited for tasks such as building orthogonally equivariant models and learning node positional encodings for link prediction in graphs. In this work, we demonstrate the benefits of sign equivariance for these tasks. To obtain these benefits, we develop novel sign equivariant neural network architectures. Our models are based on a new analytic characterization of sign equivariant polynomials and thus inherit provable expressiveness properties. Controlled synthetic experiments show that our networks can achieve the theoretically predicted benefits of sign equivariant models. Code is available at https://github.com/cptq/Sign-Equivariant-Nets.","url_abs":"https://arxiv.org/abs/2312.02339v1","url_pdf":"https://arxiv.org/pdf/2312.02339v1.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":"expressive-sign-equivariant-networks-for-1","repo_url":"https://github.com/cptq/sign-equivariant-nets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"negation","task_name":"Negation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.02339","atlas_url":"https://app.syntology.ai/?focus=2312.02339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02339"}},"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/cptq/Sign-Equivariant-Nets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cptq/sign-equivariant-nets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"0d2dcbdbeaaf0dad","entry":"BasicMLP","repo":"cptq/sign-equivariant-nets","repo_kind":"official","path":"link_pred/models.py","file_url":"https://github.com/cptq/sign-equivariant-nets/blob/HEAD/link_pred/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":"0d2dcbdbeaaf0dad"}},{"code_sha256_prefix":"06d3622aea1bc621","entry":"SignEqGateLayer","repo":"cptq/sign-equivariant-nets","repo_kind":"official","path":"link_pred/models.py","file_url":"https://github.com/cptq/sign-equivariant-nets/blob/HEAD/link_pred/models.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":"06d3622aea1bc621"}},{"code_sha256_prefix":"f7b5096e82c2d27c","entry":"NoParamConv","repo":"cptq/sign-equivariant-nets","repo_kind":"official","path":"link_pred/models.py","file_url":"https://github.com/cptq/sign-equivariant-nets/blob/HEAD/link_pred/models.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":"f7b5096e82c2d27c"}},{"code_sha256_prefix":"33ca7f45e46b97b5","entry":"SignDSS","repo":"cptq/sign-equivariant-nets","repo_kind":"official","path":"link_pred/models.py","file_url":"https://github.com/cptq/sign-equivariant-nets/blob/HEAD/link_pred/models.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":"33ca7f45e46b97b5"}},{"code_sha256_prefix":"64f02d38f2124a45","entry":"SignDSSLayer","repo":"cptq/sign-equivariant-nets","repo_kind":"official","path":"link_pred/models.py","file_url":"https://github.com/cptq/sign-equivariant-nets/blob/HEAD/link_pred/models.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":"64f02d38f2124a45"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}