{"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/attention-as-a-hypernetwork","title":"Attention as a Hypernetwork","arxiv_id":"2406.05816","date":"2024-06-09","proceeding":null,"authors":["Simon Schug","Seijin Kobayashi","Yassir Akram","João Sacramento","Razvan Pascanu"],"abstract":"Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training but whose compositions have not. What mechanisms underlie this ability for compositional generalization? By reformulating multi-head attention as a hypernetwork, we reveal that a composable, low-dimensional latent code specifies key-query specific operations. We find empirically that this latent code is predictive of the subtasks the network performs on unseen task compositions revealing that latent codes acquired during training are reused to solve unseen problem instances. To further examine the hypothesis that the intrinsic hypernetwork of multi-head attention supports compositional generalization, we ablate whether making the hypernetwork generated linear value network nonlinear strengthens compositionality. We find that this modification improves compositional generalization on abstract reasoning tasks. In particular, we introduce a symbolic version of the Raven Progressive Matrices human intelligence test which gives us precise control over the problem compositions encountered during training and evaluation. We demonstrate on this task how scaling model size and data enables compositional generalization in transformers and gives rise to a functionally structured latent space.","url_abs":"https://arxiv.org/abs/2406.05816v3","url_pdf":"https://arxiv.org/pdf/2406.05816v3.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":"attention-as-a-hypernetwork","repo_url":"https://github.com/smonsays/hypernetwork-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"multi-head-linear-attention","method_name":"Multi-Head Linear Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.05816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05816"}},"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/smonsays/hypernetwork-attention","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":"7b16566f5fe35f8e","entry":"dict_filter","repo":"smonsays/hypernetwork-attention","repo_kind":"official","path":"hyla/utils/dict.py","file_url":"https://github.com/smonsays/hypernetwork-attention/blob/HEAD/hyla/utils/dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b16566f5fe35f8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}