{"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/finding-the-pillars-of-strength-for-multi","title":"Finding the Pillars of Strength for Multi-Head Attention","arxiv_id":"2305.14380","date":"2023-05-22","proceeding":null,"authors":["Jinjie Ni","Rui Mao","Zonglin Yang","Han Lei","Erik Cambria"],"abstract":"Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming performance. Inspired by the minimum-redundancy feature selection, we assume that focusing on the most representative and distinctive features with minimum resources can mitigate the above issues and lead to more effective and efficient MHAs. In particular, we propose Grouped Head Attention, trained with a self-supervised group constraint that group attention heads, where each group focuses on an essential but distinctive feature subset. We additionally propose a Voting-to-Stay procedure to remove redundant heads, thus achieving a transformer with lighter weights. Moreover, our method achieves significant performance gains on three well-established tasks while considerably compressing parameters.","url_abs":"https://arxiv.org/abs/2305.14380v2","url_pdf":"https://arxiv.org/pdf/2305.14380v2.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":"finding-the-pillars-of-strength-for-multi","repo_url":"https://github.com/psycoy/acl-2023-grouped-head-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"finding-the-pillars-of-strength-for-multi","repo_url":"https://github.com/senticnet/gha","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.14380","atlas_url":"https://app.syntology.ai/?focus=2305.14380","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2305.14380"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.14380\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.14380"},"call":"get_concepts_for_paper(arxiv_id=\"2305.14380\")"}],"by_repo":[{"repo":"psycoy/acl-2023-grouped-head-attention","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"senticnet/gha","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4c6f44bdf9763fbe36ad8695e67c3b7665ac86c1f706c25ab580152635c37da9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}