{"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/efficient-long-sequence-modeling-via-state","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","arxiv_id":"2212.08136","date":"2022-12-15","proceeding":null,"authors":["Simiao Zuo","Xiaodong Liu","Jian Jiao","Denis Charles","Eren Manavoglu","Tuo Zhao","Jianfeng Gao"],"abstract":"Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing attention variants that improve the computational efficiency, but they have limited ability to effectively compute global information. In parallel to Transformer models, state space models (SSMs) are tailored for long sequences, but they are not flexible enough to capture complicated local information. We propose SPADE, short for $\\underline{\\textbf{S}}$tate s$\\underline{\\textbf{P}}$ace $\\underline{\\textbf{A}}$ugmente$\\underline{\\textbf{D}}$ Transform$\\underline{\\textbf{E}}$r. Specifically, we augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. The SSM augments global information, which complements the lack of long-range dependency issue in local attention methods. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method. To further demonstrate the scalability of SPADE, we pre-train large encoder-decoder models and present fine-tuning results on natural language understanding and natural language generation tasks.","url_abs":"https://arxiv.org/abs/2212.08136v1","url_pdf":"https://arxiv.org/pdf/2212.08136v1.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":"efficient-long-sequence-modeling-via-state","repo_url":"https://github.com/microsoft/efficientlongsequencemodeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"text-generation","task_name":"Text Generation"}],"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":"spade","method_name":"SPADE"},{"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=2212.08136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08136"}},"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/microsoft/efficientlongsequencemodeling","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"89b10a8b26bbb7ed","entry":"Activation","repo":"microsoft/efficientlongsequencemodeling","repo_kind":"official","path":"spade-modules/s4.py","file_url":"https://github.com/microsoft/efficientlongsequencemodeling/blob/HEAD/spade-modules/s4.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89b10a8b26bbb7ed"}},{"code_sha256_prefix":"898daef1784ec4bd","entry":"LinearActivation","repo":"microsoft/efficientlongsequencemodeling","repo_kind":"official","path":"spade-modules/s4.py","file_url":"https://github.com/microsoft/efficientlongsequencemodeling/blob/HEAD/spade-modules/s4.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"898daef1784ec4bd"}},{"code_sha256_prefix":"348275db42a37bee","entry":"power","repo":"microsoft/efficientlongsequencemodeling","repo_kind":"official","path":"spade-modules/s4.py","file_url":"https://github.com/microsoft/efficientlongsequencemodeling/blob/HEAD/spade-modules/s4.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"348275db42a37bee"}},{"code_sha256_prefix":"3e6ba755ef541738","entry":"get_local_attention_mask","repo":"microsoft/efficientlongsequencemodeling","repo_kind":"official","path":"spade-modules/local_attention.py","file_url":"https://github.com/microsoft/efficientlongsequencemodeling/blob/HEAD/spade-modules/local_attention.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":"3e6ba755ef541738"}},{"code_sha256_prefix":"99c73b17bb69ab80","entry":"make_3block_relative_position_ids","repo":"microsoft/efficientlongsequencemodeling","repo_kind":"official","path":"spade-modules/local_attention.py","file_url":"https://github.com/microsoft/efficientlongsequencemodeling/blob/HEAD/spade-modules/local_attention.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":"99c73b17bb69ab80"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}