{"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/hypformer-exploring-efficient-hyperbolic","title":"Hypformer: Exploring Efficient Hyperbolic Transformer Fully in Hyperbolic Space","arxiv_id":"2407.01290","date":"2024-07-01","proceeding":null,"authors":["Menglin Yang","Harshit Verma","Delvin Ce Zhang","Jiahong Liu","Irwin King","Rex Ying"],"abstract":"Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks across numerous domains, research on adapting the Transformer to hyperbolic space remains limited. Previous attempts have mainly focused on modifying self-attention modules in the Transformer. However, these efforts have fallen short of developing a complete hyperbolic Transformer. This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. In Hypformer, we introduce two foundational blocks that define the essential modules of the Transformer in hyperbolic space. Furthermore, we develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time. Our experimental results confirm the effectiveness and efficiency of Hypformer across various datasets, demonstrating its potential as an effective and scalable solution for large-scale data representation and large models.","url_abs":"https://arxiv.org/abs/2407.01290v1","url_pdf":"https://arxiv.org/pdf/2407.01290v1.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":"hypformer-exploring-efficient-hyperbolic","repo_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01290"}},"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/Graph-and-Geometric-Learning/hyperbolic-transformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"de5bdf76ff672322","entry":"class_rand_splits","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/data_utils.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/data_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":"de5bdf76ff672322"}},{"code_sha256_prefix":"8a190827898c38bb","entry":"get_device","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/main-batch.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/main-batch.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":"8a190827898c38bb"}},{"code_sha256_prefix":"ef6b5e211f3c0418","entry":"load_fixed_splits","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/data_utils.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/data_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":"ef6b5e211f3c0418"}},{"code_sha256_prefix":"5c5f4efd8c517968","entry":"mkdirs","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/logger.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/logger.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":"5c5f4efd8c517968"}},{"code_sha256_prefix":"67fc014db49b3eba","entry":"load_fb100","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/load_data.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/load_data.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":"67fc014db49b3eba"}},{"code_sha256_prefix":"985aeae95edfd025","entry":"load_twitch","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/load_data.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/load_data.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":"985aeae95edfd025"}},{"code_sha256_prefix":"13234652741e2264","entry":"rand_train_test_idx","repo":"Graph-and-Geometric-Learning/hyperbolic-transformer","repo_kind":"official","path":"large/data_utils.py","file_url":"https://github.com/Graph-and-Geometric-Learning/hyperbolic-transformer/blob/HEAD/large/data_utils.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":"13234652741e2264"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}