{"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/h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","arxiv_id":"2107.11906","date":"2021-07-25","proceeding":"ACL 2021 5","authors":["Zhenhai Zhu","Radu Soricut"],"abstract":"We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical analysis community, and has linear run time and memory complexity. We perform extensive experiments to show that the inductive bias embodied by our hierarchical attention is effective in capturing the hierarchical structure in the sequences typical for natural language and vision tasks. Our method is superior to alternative sub-quadratic proposals by over +6 points on average on the Long Range Arena benchmark. It also sets a new SOTA test perplexity on One-Billion Word dataset with 5x fewer model parameters than that of the previous-best Transformer-based models.","url_abs":"https://arxiv.org/abs/2107.11906v1","url_pdf":"https://arxiv.org/pdf/2107.11906v1.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":"h-transformer-1d-fast-one-dimensional","repo_url":"https://github.com/lucidrains/h-transformer-1d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"h-transformer-1d-fast-one-dimensional","repo_url":"https://github.com/jinmang2/hierarchical-transformer-1d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"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":[{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"H-Transformer-1D Nr=16 (Base)","rank_in_archive_order":26,"of":27,"metrics":{"Number of params":"53M","Validation perplexity":"23.95"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"H-Transformer-1D Nr=16 (Large)","rank_in_archive_order":27,"of":27,"metrics":{"Number of params":"144M","Validation perplexity":"20.25"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.11906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11906"}},"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/jinmang2/hierarchical-transformer-1d","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/h-transformer-1d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":3,"ran_violates":1,"unverified":5},"by_repo_kind":{"listed":{"samples":10,"ran":5,"repositories":2}},"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":"e3b0303428abb577","entry":"HTransformer1DRotaryEmbedding","repo":"jinmang2/hierarchical-transformer-1d","repo_kind":"listed","path":"src/modeling_htransformer1d.py","file_url":"https://github.com/jinmang2/hierarchical-transformer-1d/blob/HEAD/src/modeling_htransformer1d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3b0303428abb577"}},{"code_sha256_prefix":"c16aee9490eb8729","entry":"eval_decorator","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/autoregressive_wrapper.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c16aee9490eb8729"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/autoregressive_wrapper.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"8a5b2cb4b5962883","entry":"flip_every_two","repo":"jinmang2/hierarchical-transformer-1d","repo_kind":"listed","path":"src/modeling_htransformer1d.py","file_url":"https://github.com/jinmang2/hierarchical-transformer-1d/blob/HEAD/src/modeling_htransformer1d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a5b2cb4b5962883"}},{"code_sha256_prefix":"3b65d5d77510c964","entry":"top_k","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/autoregressive_wrapper.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/autoregressive_wrapper.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b65d5d77510c964"}},{"code_sha256_prefix":"0264a115409ab8db","entry":"HTransformer1DAttention","repo":"jinmang2/hierarchical-transformer-1d","repo_kind":"listed","path":"src/modeling_htransformer1d.py","file_url":"https://github.com/jinmang2/hierarchical-transformer-1d/blob/HEAD/src/modeling_htransformer1d.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":"0264a115409ab8db"}},{"code_sha256_prefix":"a5d582ae0f1134fb","entry":"layer_drop","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/reversible.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/reversible.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":"a5d582ae0f1134fb"}},{"code_sha256_prefix":"b651f49b40613305","entry":"masked_aggregate","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/h_transformer_1d.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/h_transformer_1d.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":"b651f49b40613305"}},{"code_sha256_prefix":"1f7d4befc2e41402","entry":"route_args","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/reversible.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/reversible.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":"1f7d4befc2e41402"}},{"code_sha256_prefix":"f73845c2459404f2","entry":"shift","repo":"lucidrains/h-transformer-1d","repo_kind":"listed","path":"h_transformer_1d/h_transformer_1d.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/h_transformer_1d.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":"f73845c2459404f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}