{"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/reds-resource-efficient-deep-subnetworks-for","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","arxiv_id":"2311.13349","date":"2023-11-22","proceeding":null,"authors":["Francesco Corti","Balz Maag","Joachim Schauer","Ulrich Pferschy","Olga Saukh"],"abstract":"Deep models deployed on edge devices frequently encounter resource variability, which arises from fluctuating energy levels, timing constraints, or prioritization of other critical tasks within the system. State-of-the-art machine learning pipelines generate resource-agnostic models, not capable to adapt at runtime. In this work we introduce Resource-Efficient Deep Subnetworks (REDS) to tackle model adaptation to variable resources. In contrast to the state-of-the-art, REDS use structured sparsity constructively by exploiting permutation invariance of neurons, which allows for hardware-specific optimizations. Specifically, REDS achieve computational efficiency by (1) skipping sequential computational blocks identified by a novel iterative knapsack optimizer, and (2) leveraging simple math to re-arrange the order of operations in REDS computational graph to take advantage of the data cache. REDS support conventional deep networks frequently deployed on the edge and provide computational benefits even for small and simple networks. We evaluate REDS on seven benchmark architectures trained on the Visual Wake Words, Google Speech Commands, Fashion-MNIST and CIFAR10 datasets, and test on four off-the-shelf mobile and embedded hardware platforms. We provide a theoretical result and empirical evidence for REDS outstanding performance in terms of submodels' test set accuracy, and demonstrate an adaptation time in response to dynamic resource constraints of under 40$\\mu$s, utilizing a 2-layer fully-connected network on Arduino Nano 33 BLE.","url_abs":"https://arxiv.org/abs/2311.13349v2","url_pdf":"https://arxiv.org/pdf/2311.13349v2.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":"reds-resource-efficient-deep-subnetworks-for","repo_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.13349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13349"}},"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/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","reach":{"status":"ok"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"611d0ca83b814284","entry":"create_dnn_model_gpu","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/keyword_spotting_models.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/keyword_spotting_models.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":"611d0ca83b814284"}},{"code_sha256_prefix":"8e328473e54213dd","entry":"create_single_fc_model","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/keyword_spotting_models.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/keyword_spotting_models.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":"8e328473e54213dd"}},{"code_sha256_prefix":"192dd9061e6f5d15","entry":"get_feature_extraction_layers_gradient_indexes","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/importance_score.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/importance_score.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":"192dd9061e6f5d15"}},{"code_sha256_prefix":"5e3fb03f063c424b","entry":"get_fully_connected_layers_gradient_indexes","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/importance_score.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/importance_score.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":"5e3fb03f063c424b"}},{"code_sha256_prefix":"c0acf0e6b799b7c9","entry":"get_pointwise_layers_gradients_indexes","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/importance_score.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/importance_score.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":"c0acf0e6b799b7c9"}},{"code_sha256_prefix":"f76c8842dec663f5","entry":"load_pre_trained_vision_model","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/vision_models.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/vision_models.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":"f76c8842dec663f5"}},{"code_sha256_prefix":"807314b9eabf6aad","entry":"prepare_model_settings","repo":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","repo_kind":"official","path":"utils/keyword_spotting_models.py","file_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints/blob/HEAD/utils/keyword_spotting_models.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":"807314b9eabf6aad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}