{"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/differentially-private-mean-embeddings-with","title":"DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation","arxiv_id":"2002.11603","date":"2020-02-26","proceeding":null,"authors":["Frederik Harder","Kamil Adamczewski","Mijung Park"],"abstract":"We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data. We exploit the random feature representations for two important benefits. First, we require a minimal privacy cost for training deep generative models. This is because unlike kernel-based distance metrics that require computing the kernel matrix on all pairs of true and synthetic data points, we can detach the data-dependent term from the term solely dependent on synthetic data. Hence, we need to perturb the data-dependent term only once and then use it repeatedly during the generator training. Second, we can obtain an analytic sensitivity of the kernel mean embedding as the random features are norm bounded by construction. This removes the necessity of hyper-parameter search for a clipping norm to handle the unknown sensitivity of a generator network. We provide several variants of our algorithm, differentially-private mean embeddings with random features (DP-MERF) to jointly generate labels and input features for datasets such as heterogeneous tabular data and image data. Our algorithm achieves drastically better privacy-utility trade-offs than existing methods when tested on several datasets.","url_abs":"https://arxiv.org/abs/2002.11603v5","url_pdf":"https://arxiv.org/pdf/2002.11603v5.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":"differentially-private-mean-embeddings-with","repo_url":"https://github.com/ParkLabML/DP-MERF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.11603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11603"}},"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/ParkLabML/DP-MERF","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"4cb0ce65a31979d0","entry":"Feature_labels","repo":"ParkLabML/DP-MERF","repo_kind":"official","path":"code_tab/single_generator_priv_all.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_tab/single_generator_priv_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb0ce65a31979d0"}},{"code_sha256_prefix":"2d0dfe12ad42510c","entry":"RFF_Gauss","repo":"ParkLabML/DP-MERF","repo_kind":"official","path":"code_tab/single_generator_priv_all.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_tab/single_generator_priv_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d0dfe12ad42510c"}},{"code_sha256_prefix":"bc7be881b0212aab","entry":"undersample","repo":"ParkLabML/DP-MERF","repo_kind":"official","path":"code_tab/single_generator_priv_all.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_tab/single_generator_priv_all.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":"bc7be881b0212aab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}