{"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/scalable-and-efficient-training-of-large","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","arxiv_id":"2205.10683","date":"2022-05-21","proceeding":null,"authors":["Zhiqi Bu","Jialin Mao","Shiyun Xu"],"abstract":"Large convolutional neural networks (CNN) can be difficult to train in the differentially private (DP) regime, since the optimization algorithms require a computationally expensive operation, known as the per-sample gradient clipping. We propose an efficient and scalable implementation of this clipping on convolutional layers, termed as the mixed ghost clipping, that significantly eases the private training in terms of both time and space complexities, without affecting the accuracy. The improvement in efficiency is rigorously studied through the first complexity analysis for the mixed ghost clipping and existing DP training algorithms. Extensive experiments on vision classification tasks, with large ResNet, VGG, and Vision Transformers, demonstrate that DP training with mixed ghost clipping adds $1\\sim 10\\%$ memory overhead and $<2\\times$ slowdown to the standard non-private training. Specifically, when training VGG19 on CIFAR10, the mixed ghost clipping is $3\\times$ faster than state-of-the-art Opacus library with $18\\times$ larger maximum batch size. To emphasize the significance of efficient DP training on convolutional layers, we achieve 96.7\\% accuracy on CIFAR10 and 83.0\\% on CIFAR100 at $\\epsilon=1$ using BEiT, while the previous best results are 94.8\\% and 67.4\\%, respectively. We open-source a privacy engine (\\url{https://github.com/woodyx218/private_vision}) that implements DP training of CNN with a few lines of code.","url_abs":"https://arxiv.org/abs/2205.10683v4","url_pdf":"https://arxiv.org/pdf/2205.10683v4.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":"scalable-and-efficient-training-of-large","repo_url":"https://github.com/woodyx218/private_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.10683","atlas_url":"https://app.syntology.ai/?focus=2205.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10683"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/woodyx218/private_","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/woodyx218/private_vision","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"eeeeac55e0de9d93","entry":"_light_linear_weight_norm_sample_sequential","repo":"woodyx218/private_vision","repo_kind":"official","path":"private_vision/supported_layers_grad_samplers.py","file_url":"https://github.com/woodyx218/private_vision/blob/HEAD/private_vision/supported_layers_grad_samplers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eeeeac55e0de9d93"}},{"code_sha256_prefix":"07bd2b802db4e7f1","entry":"get_sigma_from_gdp","repo":"woodyx218/private_vision","repo_kind":"official","path":"private_vision/privacy_engine.py","file_url":"https://github.com/woodyx218/private_vision/blob/HEAD/private_vision/privacy_engine.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":"07bd2b802db4e7f1"}},{"code_sha256_prefix":"fe86df433c0fa05e","entry":"get_sigma_from_rdp","repo":"woodyx218/private_vision","repo_kind":"official","path":"private_vision/privacy_engine.py","file_url":"https://github.com/woodyx218/private_vision/blob/HEAD/private_vision/privacy_engine.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":"fe86df433c0fa05e"}},{"code_sha256_prefix":"b83af4f60add8bbc","entry":"get_sigma_from_rdp_cks","repo":"woodyx218/private_vision","repo_kind":"official","path":"private_vision/privacy_engine.py","file_url":"https://github.com/woodyx218/private_vision/blob/HEAD/private_vision/privacy_engine.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":"b83af4f60add8bbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}