{"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/spike-driven-transformer-1","title":"Spike-driven Transformer","arxiv_id":"2307.01694","date":"2023-07-04","proceeding":"NeurIPS 2023 11","authors":["Man Yao","Jiakui Hu","Zhaokun Zhou","Li Yuan","Yonghong Tian","Bo Xu","Guoqi Li"],"abstract":"Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: 1) Event-driven, no calculation is triggered when the input of Transformer is zero; 2) Binary spike communication, all matrix multiplications associated with the spike matrix can be transformed into sparse additions; 3) Self-attention with linear complexity at both token and channel dimensions; 4) The operations between spike-form Query, Key, and Value are mask and addition. Together, there are only sparse addition operations in the Spike-driven Transformer. To this end, we design a novel Spike-Driven Self-Attention (SDSA), which exploits only mask and addition operations without any multiplication, and thus having up to $87.2\\times$ lower computation energy than vanilla self-attention. Especially in SDSA, the matrix multiplication between Query, Key, and Value is designed as the mask operation. In addition, we rearrange all residual connections in the vanilla Transformer before the activation functions to ensure that all neurons transmit binary spike signals. It is shown that the Spike-driven Transformer can achieve 77.1\\% top-1 accuracy on ImageNet-1K, which is the state-of-the-art result in the SNN field. The source code is available at https://github.com/BICLab/Spike-Driven-Transformer.","url_abs":"https://arxiv.org/abs/2307.01694v1","url_pdf":"https://arxiv.org/pdf/2307.01694v1.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":"spike-driven-transformer-1","repo_url":"https://github.com/biclab/spike-driven-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"snn","method_name":"SNN"},{"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=2307.01694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01694"}},"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/biclab/spike-driven-transformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"a71accca7675fc44","entry":"TET_loss","repo":"biclab/spike-driven-transformer","repo_kind":"official","path":"criterion.py","file_url":"https://github.com/biclab/spike-driven-transformer/blob/HEAD/criterion.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a71accca7675fc44"}},{"code_sha256_prefix":"1fa0df834a6e5df1","entry":"drop_by_area","repo":"biclab/spike-driven-transformer","repo_kind":"official","path":"dvs_utils/dvs_augment.py","file_url":"https://github.com/biclab/spike-driven-transformer/blob/HEAD/dvs_utils/dvs_augment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fa0df834a6e5df1"}},{"code_sha256_prefix":"096d3cc0ddfddc9a","entry":"drop_by_time","repo":"biclab/spike-driven-transformer","repo_kind":"official","path":"dvs_utils/dvs_augment.py","file_url":"https://github.com/biclab/spike-driven-transformer/blob/HEAD/dvs_utils/dvs_augment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"096d3cc0ddfddc9a"}},{"code_sha256_prefix":"101efd23952db50b","entry":"event_drop","repo":"biclab/spike-driven-transformer","repo_kind":"official","path":"dvs_utils/dvs_augment.py","file_url":"https://github.com/biclab/spike-driven-transformer/blob/HEAD/dvs_utils/dvs_augment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"101efd23952db50b"}},{"code_sha256_prefix":"4760b7f7cbe7cd94","entry":"split_to_train_test_set","repo":"biclab/spike-driven-transformer","repo_kind":"official","path":"dvs_utils/dvs_utils.py","file_url":"https://github.com/biclab/spike-driven-transformer/blob/HEAD/dvs_utils/dvs_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4760b7f7cbe7cd94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}