{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-dot-product-attention-free-transformer","title":"A Dot Product Attention Free Transformer","arxiv_id":null,"date":"2021-09-29","proceeding":null,"authors":["Shuangfei Zhai","Walter Talbott","Nitish Srivastava","Chen Huang","Hanlin Goh","Ruixiang Zhang","Joshua M. Susskind"],"abstract":"We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \\citep{transformer} that eliminates the query-key dot product in self attention. The core idea is to construct a decomposable attention map for each dimension of the query, key and value. This compositionality enables an implementation where the attention tensor does not to be computed or stored explicitly. A DAFT layer has a memory complexity linear w.r.t. both the context size and the dimension of features, making it compatible with both large input and model sizes. We also introduce DAFT-conv, a model variant that takes advantage of locality and spatial weight sharing while maintaining global connectivity. We conduct experiments on ImageNet-1K classification, as well as CIFAR10 and Enwik8, two autoregressive modeling tasks. We show that DAFT demonstrates competitive performance on all the benchmarks, while providing excellent efficiency at the same time.","url_abs":"https://openreview.net/forum?id=JVR4JswsEM","url_pdf":"https://openreview.net/pdf?id=JVR4JswsEM","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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"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":"attention-free-transformer","method_name":"Attention Free Transformer"},{"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/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DAFT-conv (384 heads, 300 epochs)","rank_in_archive_order":682,"of":1060,"metrics":{"Number of params":"23M","Top 1 Accuracy":"80.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DAFT-conv (16 heads)","rank_in_archive_order":714,"of":1060,"metrics":{"Number of params":"20.3M","Top 1 Accuracy":"80.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DAFT-conv (384 heads, 200 epochs)","rank_in_archive_order":718,"of":1060,"metrics":{"Number of params":"23M","Top 1 Accuracy":"80.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DAFT-full","rank_in_archive_order":742,"of":1060,"metrics":{"Number of params":"22.6M","Top 1 Accuracy":"79.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"467fd626647cc2a9ee60d04725ea3d43114bb2ea910d8433941eded690fa19ad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}