{"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/pranc-pseudo-random-networks-for-compacting","title":"PRANC: Pseudo RAndom Networks for Compacting deep models","arxiv_id":"2206.08464","date":"2022-06-16","proceeding":"ICCV 2023 1","authors":["Parsa Nooralinejad","Ali Abbasi","Soroush Abbasi Koohpayegani","Kossar Pourahmadi Meibodi","Rana Muhammad Shahroz Khan","Soheil Kolouri","Hamed Pirsiavash"],"abstract":"We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek local minima that reside within the subspace spanned by these random models (i.e., `basis' networks). Our framework, PRANC, enables significant compaction of a deep model. The model can be reconstructed using a single scalar `seed,' employed to generate the pseudo-random `basis' networks, together with the learned linear mixture coefficients. In practical applications, PRANC addresses the challenge of efficiently storing and communicating deep models, a common bottleneck in several scenarios, including multi-agent learning, continual learners, federated systems, and edge devices, among others. In this study, we employ PRANC to condense image classification models and compress images by compacting their associated implicit neural networks. PRANC outperforms baselines with a large margin on image classification when compressing a deep model almost $100$ times. Moreover, we show that PRANC enables memory-efficient inference by generating layer-wise weights on the fly. The source code of PRANC is here: \\url{https://github.com/UCDvision/PRANC}","url_abs":"https://arxiv.org/abs/2206.08464v2","url_pdf":"https://arxiv.org/pdf/2206.08464v2.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":"pranc-pseudo-random-networks-for-compacting","repo_url":"https://github.com/ucdvision/pranc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pranc-pseudo-random-networks-for-compacting","repo_url":"https://github.com/Guang000/Awesome-Dataset-Distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.08464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08464"}},"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/Guang000/Awesome-Dataset-Distillation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucdvision/pranc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"5a9c45aaf6f7c743","entry":"DataLoader","repo":"ucdvision/pranc","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/dataloader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a9c45aaf6f7c743"}},{"code_sha256_prefix":"c1470f38857db067","entry":"gather_all_test","repo":"ucdvision/pranc","repo_kind":"official","path":"main_distrib.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/main_distrib.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1470f38857db067"}},{"code_sha256_prefix":"559a1b7ac7031f22","entry":"has_batchnorm","repo":"ucdvision/pranc","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"559a1b7ac7031f22"}},{"code_sha256_prefix":"78d8e5e6e66e350d","entry":"init_alpha","repo":"ucdvision/pranc","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78d8e5e6e66e350d"}},{"code_sha256_prefix":"ab0e29f62181fe49","entry":"prancable","repo":"ucdvision/pranc","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab0e29f62181fe49"}},{"code_sha256_prefix":"d55fb109c7acd1c1","entry":"resnet18","repo":"ucdvision/pranc","repo_kind":"official","path":"models.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d55fb109c7acd1c1"}},{"code_sha256_prefix":"ee582e3134b37493","entry":"resnet20","repo":"ucdvision/pranc","repo_kind":"official","path":"models.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee582e3134b37493"}},{"code_sha256_prefix":"9f559415fc5c03d7","entry":"resnet56","repo":"ucdvision/pranc","repo_kind":"official","path":"models.py","file_url":"https://github.com/ucdvision/pranc/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f559415fc5c03d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}