{"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/can-neural-network-memorization-be-localized","title":"Can Neural Network Memorization Be Localized?","arxiv_id":"2307.09542","date":"2023-07-18","proceeding":null,"authors":["Pratyush Maini","Michael C. Mozer","Hanie Sedghi","Zachary C. Lipton","J. Zico Kolter","Chiyuan Zhang"],"abstract":"Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks $\\textit{memorize}$ \"hard\" examples in the final few layers of the model. Memorization refers to the ability to correctly predict on $\\textit{atypical}$ examples of the training set. In this work, we show that rather than being confined to individual layers, memorization is a phenomenon confined to a small set of neurons in various layers of the model. First, via three experimental sources of converging evidence, we find that most layers are redundant for the memorization of examples and the layers that contribute to example memorization are, in general, not the final layers. The three sources are $\\textit{gradient accounting}$ (measuring the contribution to the gradient norms from memorized and clean examples), $\\textit{layer rewinding}$ (replacing specific model weights of a converged model with previous training checkpoints), and $\\textit{retraining}$ (training rewound layers only on clean examples). Second, we ask a more generic question: can memorization be localized $\\textit{anywhere}$ in a model? We discover that memorization is often confined to a small number of neurons or channels (around 5) of the model. Based on these insights we propose a new form of dropout -- $\\textit{example-tied dropout}$ that enables us to direct the memorization of examples to an apriori determined set of neurons. By dropping out these neurons, we are able to reduce the accuracy on memorized examples from $100\\%\\to3\\%$, while also reducing the generalization gap.","url_abs":"https://arxiv.org/abs/2307.09542v1","url_pdf":"https://arxiv.org/pdf/2307.09542v1.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":"can-neural-network-memorization-be-localized","repo_url":"https://github.com/pratyushmaini/localizing-memorization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"memorization","task_name":"Memorization"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.09542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09542"}},"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/pratyushmaini/localizing-memorization","reach":null}],"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":1,"samples":[{"code_sha256_prefix":"95a25fb3c702c3cd","entry":"ExampleTiedDropout","repo":"pratyushmaini/localizing-memorization","repo_kind":"official","path":"models/dropout.py","file_url":"https://github.com/pratyushmaini/localizing-memorization/blob/HEAD/models/dropout.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95a25fb3c702c3cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}