{"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/fully-hyperbolic-neural-networks","title":"Fully Hyperbolic Neural Networks","arxiv_id":"2105.14686","date":"2021-05-31","proceeding":"ACL 2022 5","authors":["Weize Chen","Xu Han","Yankai Lin","Hexu Zhao","Zhiyuan Liu","Peng Li","Maosong Sun","Jie zhou"],"abstract":"Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in a hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic space. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operations of neural networks. Moreover, we also prove that linear transformation in tangent spaces used by existing hyperbolic networks is a relaxation of the Lorentz rotation and does not include the boost, implicitly limiting the capabilities of existing hyperbolic networks. The experimental results on four NLP tasks show that our method has better performance for building both shallow and deep networks. Our code will be released to facilitate follow-up research.","url_abs":"https://arxiv.org/abs/2105.14686v3","url_pdf":"https://arxiv.org/pdf/2105.14686v3.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":"fully-hyperbolic-neural-networks","repo_url":"https://github.com/chenweize1998/fully-hyperbolic-nn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fully-hyperbolic-neural-networks","repo_url":"https://github.com/chromaprim/HybowaveNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.14686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14686"}},"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/chenweize1998/fully-hyperbolic-nn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chromaprim/HybowaveNet","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"5a890d31b81d5078","entry":"get_dim_act_curv","repo":"chenweize1998/fully-hyperbolic-nn","repo_kind":"official","path":"gcn/layers/hyp_layers.py","file_url":"https://github.com/chenweize1998/fully-hyperbolic-nn/blob/HEAD/gcn/layers/hyp_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a890d31b81d5078"}},{"code_sha256_prefix":"d5750f97b49f9b00","entry":"lorentz_linear","repo":"chenweize1998/fully-hyperbolic-nn","repo_kind":"official","path":"kg/LorentzModel.py","file_url":"https://github.com/chenweize1998/fully-hyperbolic-nn/blob/HEAD/kg/LorentzModel.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5750f97b49f9b00"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}