{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2ALDUHX24A2SGJNNXFSWRFG2J","short_pith_number":"pith:Q2ALDUHX","schema_version":"1.0","canonical_sha256":"8680b1d0f7d701a9192d6dcb2b44a6d257043574709c8818e2b356c0b20f0286","source":{"kind":"arxiv","id":"2405.19272","version":6},"attestation_state":"computed","paper":{"title":"Differentially Private Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Afaf Taik, Golnoosh Farnadi, Saber Malekmohammadi","submitted_at":"2024-05-29T17:03:31Z","abstract_excerpt":"Federated learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to provide rigorous data privacy guarantees. Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL), but these methods remain sensitive and prone to errors, further exacerbated by the DP noise. This vulnerability makes the previous methods inappropriate for differentially private FL (DPFL) settings with structured data heterogeneity. To address this gap, we propose an algorithm for d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.19272","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:03:31Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"61c2a7a50bf8e505694b38dedd265d426f822c640a85d3be9b78e91b78cc9961","abstract_canon_sha256":"a40c2df413a066a631eda4a8d3a1bb8a8f199abb8f32d0df67676bcccbc13b79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:21.307210Z","signature_b64":"psfzdSsQ2BJInKgvjyIM4XjW6CAS10ITfnA447FpHzbiun8PV2B7n6d20uZzTh0a1JXQIUfBC3vQrqSUEkLBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8680b1d0f7d701a9192d6dcb2b44a6d257043574709c8818e2b356c0b20f0286","last_reissued_at":"2026-07-05T10:55:21.306713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:21.306713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Afaf Taik, Golnoosh Farnadi, Saber Malekmohammadi","submitted_at":"2024-05-29T17:03:31Z","abstract_excerpt":"Federated learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to provide rigorous data privacy guarantees. Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL), but these methods remain sensitive and prone to errors, further exacerbated by the DP noise. This vulnerability makes the previous methods inappropriate for differentially private FL (DPFL) settings with structured data heterogeneity. To address this gap, we propose an algorithm for d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19272","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.19272/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.19272","created_at":"2026-07-05T10:55:21.306769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19272v6","created_at":"2026-07-05T10:55:21.306769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19272","created_at":"2026-07-05T10:55:21.306769+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2ALDUHX24A2","created_at":"2026-07-05T10:55:21.306769+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2ALDUHX24A2SGJN","created_at":"2026-07-05T10:55:21.306769+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2ALDUHX","created_at":"2026-07-05T10:55:21.306769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00799","citing_title":"Fairness in Federated Learning: Trends, Challenges, and Opportunities","ref_index":97,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J","json":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J.json","graph_json":"https://pith.science/api/pith-number/Q2ALDUHX24A2SGJNNXFSWRFG2J/graph.json","events_json":"https://pith.science/api/pith-number/Q2ALDUHX24A2SGJNNXFSWRFG2J/events.json","paper":"https://pith.science/paper/Q2ALDUHX"},"agent_actions":{"view_html":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J","download_json":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J.json","view_paper":"https://pith.science/paper/Q2ALDUHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19272&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2ALDUHX24A2SGJNNXFSWRFG2J/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2ALDUHX24A2SGJNNXFSWRFG2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J/action/storage_attestation","attest_author":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J/action/author_attestation","sign_citation":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J/action/citation_signature","submit_replication":"https://pith.science/pith/Q2ALDUHX24A2SGJNNXFSWRFG2J/action/replication_record"}},"created_at":"2026-07-05T10:55:21.306769+00:00","updated_at":"2026-07-05T10:55:21.306769+00:00"}