{"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/highway-transformer-self-gating-enhanced-self","title":"Highway Transformer: Self-Gating Enhanced Self-Attentive Networks","arxiv_id":"2004.08178","date":"2020-04-17","proceeding":"ACL 2020 6","authors":["Yekun Chai","Shuo Jin","Xinwen Hou"],"abstract":"Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a pseudo information highway, we introduce a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. The subsidiary content-based SDU gates allow for the information flow of modulated latent embeddings through skipped connections, leading to a clear margin of convergence speed with gradient descent algorithms. We may unveil the role of gating mechanism to aid in the context-based Transformer modules, with hypothesizing that SDU gates, especially on shallow layers, could push it faster to step towards suboptimal points during the optimization process.","url_abs":"https://arxiv.org/abs/2004.08178v5","url_pdf":"https://arxiv.org/pdf/2004.08178v5.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":"highway-transformer-self-gating-enhanced-self","repo_url":"https://github.com/cyk1337/Highway-Transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"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=2004.08178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08178"}},"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/cyk1337/Highway-Transformer","reach":null}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"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":"a9c70fe8ac7a630c","entry":"MultiHeadAttn","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"a9c70fe8ac7a630c"}},{"code_sha256_prefix":"b0fef51fb76e8e85","entry":"PositionwiseFF","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"b0fef51fb76e8e85"}},{"code_sha256_prefix":"4d20788c39f1a381","entry":"RelLearnableMultiHeadAttn","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"4d20788c39f1a381"}},{"code_sha256_prefix":"a55d27cf57e0e7e6","entry":"RelMultiHeadAttn","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"a55d27cf57e0e7e6"}},{"code_sha256_prefix":"521b014e68c564ef","entry":"DecoderLayer","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"521b014e68c564ef"}},{"code_sha256_prefix":"9bcbc3b0b2d06c4c","entry":"MemTransformerLM","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"9bcbc3b0b2d06c4c"}},{"code_sha256_prefix":"35620c05ac7a8ce6","entry":"RelLearnableDecoderLayer","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"35620c05ac7a8ce6"}},{"code_sha256_prefix":"a159726e43535146","entry":"RelPartialLearnableDecoderLayer","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"a159726e43535146"}},{"code_sha256_prefix":"b232620a61168335","entry":"RelPartialLearnableMultiHeadAttn","repo":"cyk1337/Highway-Transformer","repo_kind":"official","path":"pytorch/mem_transformer.py","file_url":"https://github.com/cyk1337/Highway-Transformer/blob/HEAD/pytorch/mem_transformer.py","link_basis":"first_harvest_node","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":"b232620a61168335"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}