{"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/selective-knowledge-sharing-for-privacy","title":"Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher","arxiv_id":"2304.01731","date":"2023-04-04","proceeding":null,"authors":["Jiawei Shao","Fangzhao Wu","Jun Zhang"],"abstract":"While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. Federated distillation (FD), built upon knowledge distillation--an effective technique for transferring knowledge from a teacher model to student models--emerges as an alternative paradigm, which provides enhanced privacy guarantees and addresses model heterogeneity. Nevertheless, challenges arise due to variations in local data distributions and the absence of a well-trained teacher model, which leads to misleading and ambiguous knowledge sharing that significantly degrades model performance. To address these issues, this paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD. It includes client-side selectors and a server-side selector to accurately and precisely identify knowledge from local and ensemble predictions, respectively. Empirical studies, backed by theoretical insights, demonstrate that our approach enhances the generalization capabilities of the FD framework and consistently outperforms baseline methods.","url_abs":"https://arxiv.org/abs/2304.01731v4","url_pdf":"https://arxiv.org/pdf/2304.01731v4.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":"selective-knowledge-sharing-for-privacy","repo_url":"https://github.com/shaojiawei07/selective-fd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.01731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01731"}},"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/shaojiawei07/selective-fd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"88e73751fa22e47e","entry":"generate_softlabel","repo":"shaojiawei07/selective-fd","repo_kind":"official","path":"Selective-FD.py","file_url":"https://github.com/shaojiawei07/selective-fd/blob/HEAD/Selective-FD.py","link_basis":"harvester_set","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":"88e73751fa22e47e"}},{"code_sha256_prefix":"aab17d7075191942","entry":"generate_softlabel","repo":"shaojiawei07/selective-fd","repo_kind":"official","path":"baseline_FedMD.py","file_url":"https://github.com/shaojiawei07/selective-fd/blob/HEAD/baseline_FedMD.py","link_basis":"harvester_set","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":"aab17d7075191942"}},{"code_sha256_prefix":"3c202b73129abc9a","entry":"sample_a_mini_batch","repo":"shaojiawei07/selective-fd","repo_kind":"official","path":"Selective-FD.py","file_url":"https://github.com/shaojiawei07/selective-fd/blob/HEAD/Selective-FD.py","link_basis":"harvester_set","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":"3c202b73129abc9a"}},{"code_sha256_prefix":"ea5b79d254d0c8f7","entry":"test","repo":"shaojiawei07/selective-fd","repo_kind":"official","path":"Selective-FD.py","file_url":"https://github.com/shaojiawei07/selective-fd/blob/HEAD/Selective-FD.py","link_basis":"harvester_set","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":"ea5b79d254d0c8f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}