{"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/190910364","title":"Class-dependent Compression of Deep Neural Networks","arxiv_id":"1909.10364","date":"2019-09-23","proceeding":null,"authors":["Rahim Entezari","Olga Saukh"],"abstract":"Today's deep neural networks require substantial computation resources for their training, storage, and inference, which limits their effective use on resource-constrained devices. Many recent research activities explore different options for compressing and optimizing deep models. On the one hand, in many real-world applications, we face the data imbalance challenge, i.e. when the number of labeled instances of one class considerably outweighs the number of labeled instances of the other class. On the other hand, applications may pose a class imbalance problem, i.e. higher number of false positives produced when training a model and optimizing its performance may be tolerable, yet the number of false negatives must stay low. The problem originates from the fact that some classes are more important for the application than others, e.g. detection problems in medical and surveillance domains. Motivated by the success of the lottery ticket hypothesis, in this paper we propose an iterative deep model compression technique, which keeps the number of false negatives of the compressed model close to the one of the original model at the price of increasing the number of false positives if necessary. Our experimental evaluation using two benchmark data sets shows that the resulting compressed sub-networks 1) achieve up to 35% lower number of false negatives than the compressed model without class optimization, 2) provide an overall higher AUC_ROC measure, and 3) use up to 99% fewer parameters compared to the original network.","url_abs":"https://arxiv.org/abs/1909.10364v3","url_pdf":"https://arxiv.org/pdf/1909.10364v3.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":"190910364","repo_url":"https://github.com/rahimentezari/Sensys-ml2020","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.10364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10364"}},"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/rahimentezari/Sensys-ml2020","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":2,"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":"b215cd24009a0d36","entry":"get_one_hot","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"MobileNet/MobileNet.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/MobileNet/MobileNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b215cd24009a0d36"}},{"code_sha256_prefix":"b6e06004f7efe660","entry":"wrapped_partial","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"MobileNet/mobilenet_v1.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/MobileNet/mobilenet_v1.py","link_basis":"harvester_set","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":"b6e06004f7efe660"}},{"code_sha256_prefix":"6226f06e01e888e3","entry":"alexnet","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"models/AlexNet.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/models/AlexNet.py","link_basis":"first_harvest_node","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":"6226f06e01e888e3"}},{"code_sha256_prefix":"d4465321aa394bf1","entry":"alexnet","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"models/AlexNet2.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/models/AlexNet2.py","link_basis":"first_harvest_node","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":"d4465321aa394bf1"}},{"code_sha256_prefix":"0e2ea538c8fb0e03","entry":"alexnet","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"models/AlexNet3.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/models/AlexNet3.py","link_basis":"first_harvest_node","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":"0e2ea538c8fb0e03"}},{"code_sha256_prefix":"8697ae6dc65daae7","entry":"alexnet","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"models/CNN_3.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/models/CNN_3.py","link_basis":"first_harvest_node","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":"8697ae6dc65daae7"}},{"code_sha256_prefix":"955a24768ec4558c","entry":"alexnet","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"models/alexnet_layer_input.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/models/alexnet_layer_input.py","link_basis":"first_harvest_node","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":"955a24768ec4558c"}},{"code_sha256_prefix":"7353badf6d3508bf","entry":"count_params","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"Decon_edit.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/Decon_edit.py","link_basis":"first_harvest_node","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":"7353badf6d3508bf"}},{"code_sha256_prefix":"c3c4412f0402d0e3","entry":"my_hook4d_conv1","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"Decon_edit.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/Decon_edit.py","link_basis":"first_harvest_node","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":"c3c4412f0402d0e3"}},{"code_sha256_prefix":"90ecdfb82590ae20","entry":"my_hook4d_conv2","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"Decon_edit.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/Decon_edit.py","link_basis":"first_harvest_node","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":"90ecdfb82590ae20"}},{"code_sha256_prefix":"f7c79a5644300715","entry":"tf_confusion_metrics","repo":"rahimentezari/Sensys-ml2020","repo_kind":"official","path":"MobileNet/MobileNet.py","file_url":"https://github.com/rahimentezari/Sensys-ml2020/blob/HEAD/MobileNet/MobileNet.py","link_basis":"first_harvest_node","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":"f7c79a5644300715"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}