{"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/diffused-redundancy-in-pre-trained","title":"Diffused Redundancy in Pre-trained Representations","arxiv_id":"2306.00183","date":"2023-05-31","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a given layer exhibit a degree of diffuse redundancy, ie, any randomly chosen subset of neurons in the layer that is larger than a threshold size shares a large degree of similarity with the full layer and is able to perform similarly as the whole layer on a variety of downstream tasks. For example, a linear probe trained on $20\\%$ of randomly picked neurons from the penultimate layer of a ResNet50 pre-trained on ImageNet1k achieves an accuracy within $5\\%$ of a linear probe trained on the full layer of neurons for downstream CIFAR10 classification. We conduct experiments on different neural architectures (including CNNs and Transformers) pre-trained on both ImageNet1k and ImageNet21k and evaluate a variety of downstream tasks taken from the VTAB benchmark. We find that the loss and dataset used during pre-training largely govern the degree of diffuse redundancy and the \"critical mass\" of neurons needed often depends on the downstream task, suggesting that there is a task-inherent redundancy-performance Pareto frontier. Our findings shed light on the nature of representations learned by pre-trained deep neural networks and suggest that entire layers might not be necessary to perform many downstream tasks. We investigate the potential for exploiting this redundancy to achieve efficient generalization for downstream tasks and also draw caution to certain possible unintended consequences. Our code is available at \\url{https://github.com/nvedant07/diffused-redundancy}.","url_abs":"https://arxiv.org/abs/2306.00183v3","url_pdf":"https://arxiv.org/pdf/2306.00183v3.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":"diffused-redundancy-in-pre-trained","repo_url":"https://github.com/nvedant07/diffused-redundancy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.00183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00183"}},"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":"deterministic:regex_extraction","url":"https://github.com/nvedant07/diffused-redundancy","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nvedant07/STIR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":11},"by_repo_kind":{"found_in_text":{"samples":12,"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":"078da01e51a28471","entry":"add_args_to_parser","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/model/defaults.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/model/defaults.py","link_basis":"plan_row","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":"078da01e51a28471"}},{"code_sha256_prefix":"e96e72db9f288269","entry":"TransformedLoader","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/model/loaders.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/model/loaders.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":"e96e72db9f288269"}},{"code_sha256_prefix":"3618a159ae4e6c6f","entry":"centering","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/CKA_pytorch.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/CKA_pytorch.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":"3618a159ae4e6c6f"}},{"code_sha256_prefix":"b7b8027b897178e1","entry":"forward_models","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/attack/losses.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/attack/losses.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":"b7b8027b897178e1"}},{"code_sha256_prefix":"38eecfafc4f839af","entry":"image_plot","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/plot_helper.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/plot_helper.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":"38eecfafc4f839af"}},{"code_sha256_prefix":"1ed3811c7af7289d","entry":"kernel_HSIC","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/CKA_pytorch.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/CKA_pytorch.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":"1ed3811c7af7289d"}},{"code_sha256_prefix":"129b2365166bddfa","entry":"list_as_floats","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/helper.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/helper.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":"129b2365166bddfa"}},{"code_sha256_prefix":"eed7ebd73f4d076e","entry":"list_as_ints","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/helper.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/helper.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":"eed7ebd73f4d076e"}},{"code_sha256_prefix":"fe88a8117264e87e","entry":"list_as_strs","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/helper.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/helper.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":"fe88a8117264e87e"}},{"code_sha256_prefix":"8de5a4001dbcbb38","entry":"make_loaders","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/model/loaders.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/model/loaders.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":"8de5a4001dbcbb38"}},{"code_sha256_prefix":"603a14d591c9dfb5","entry":"rbf","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/CKA_pytorch.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/CKA_pytorch.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":"603a14d591c9dfb5"}},{"code_sha256_prefix":"71f7ddd8aa721475","entry":"setup_args","repo":"nvedant07/STIR","repo_kind":"found_in_text","path":"stir/model/train_model.py","file_url":"https://github.com/nvedant07/STIR/blob/HEAD/stir/model/train_model.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":"71f7ddd8aa721475"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}