{"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/bottlenecks-club-unifying-information","title":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","arxiv_id":"2207.04895","date":"2022-07-11","proceeding":null,"authors":["Behrooz Razeghi","Flavio P. Calmon","Deniz Gunduz","Slava Voloshynovskiy"],"abstract":"Bottleneck problems are an important class of optimization problems that have recently gained increasing attention in the domain of machine learning and information theory. They are widely used in generative models, fair machine learning algorithms, design of privacy-assuring mechanisms, and appear as information-theoretic performance bounds in various multi-user communication problems. In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the state-of-the-art literature for the information-theoretic privacy models, (ii) establishes a new interpretation of the popular generative and discriminative models, (iii) constructs new insights to the generative compression models, and (iv) can be used in the fair generative models. We first formulate the CLUB model as a complexity-constrained privacy-utility optimization problem. We then connect it with the closely related bottleneck problems, namely information bottleneck (IB), privacy funnel (PF), deterministic IB (DIB), conditional entropy bottleneck (CEB), and conditional PF (CPF). We show that the CLUB model generalizes all these problems as well as most other information-theoretic privacy models. Then, we construct the deep variational CLUB (DVCLUB) models by employing neural networks to parameterize variational approximations of the associated information quantities. Building upon these information quantities, we present unified objectives of the supervised and unsupervised DVCLUB models. Leveraging the DVCLUB model in an unsupervised setup, we then connect it with state-of-the-art generative models, such as variational auto-encoders (VAEs), generative adversarial networks (GANs), as well as the Wasserstein GAN (WGAN), Wasserstein auto-encoder (WAE), and adversarial auto-encoder (AAE) models through the optimal transport (OT) problem. We then show that the DVCLUB model can also be used in fair representation learning problems, where the goal is to mitigate the undesired bias during the training phase of a machine learning model. We conduct extensive quantitative experiments on colored-MNIST and CelebA datasets, with a public implementation available, to evaluate and analyze the CLUB model.","url_abs":"https://arxiv.org/abs/2207.04895v1","url_pdf":"https://arxiv.org/pdf/2207.04895v1.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":"bottlenecks-club-unifying-information","repo_url":"https://github.com/BehroozRazeghi/CLUB","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"privacy-preserving-deep-learning","task_name":"Privacy Preserving Deep Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.04895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04895"}},"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/BehroozRazeghi/CLUB","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"13cd80dd60cc95dc","entry":"gaussian","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/sampler.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/sampler.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":"13cd80dd60cc95dc"}},{"code_sha256_prefix":"82e27d8af6263c97","entry":"mine_loss","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/mine.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/mine.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":"82e27d8af6263c97"}},{"code_sha256_prefix":"d04634cce70ef6e2","entry":"onehot_categorical","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/sampler.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/sampler.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":"d04634cce70ef6e2"}},{"code_sha256_prefix":"02148b2138ec40d0","entry":"plot_image_grid","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/pics_tools.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/pics_tools.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":"02148b2138ec40d0"}},{"code_sha256_prefix":"da8ba3ba881fc543","entry":"plot_image_grid_with_label","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/pics_tools.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/pics_tools.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":"da8ba3ba881fc543"}},{"code_sha256_prefix":"dcb7882ba2120be4","entry":"shuffle","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/mine.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/mine.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":"dcb7882ba2120be4"}},{"code_sha256_prefix":"09b4e557982cb315","entry":"uniform","repo":"BehroozRazeghi/CLUB","repo_kind":"official","path":"utils/sampler.py","file_url":"https://github.com/BehroozRazeghi/CLUB/blob/HEAD/utils/sampler.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":"09b4e557982cb315"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}