{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GY4SL5J5G4BBTKHHDHBESDIOEN","short_pith_number":"pith:GY4SL5J5","schema_version":"1.0","canonical_sha256":"363925f53d370219a8e719c2490d0e235aba08edd12ff8dbf1e7cbf5c956b6ef","source":{"kind":"arxiv","id":"2110.15252","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning with Heterogeneous Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ahmad Beirami, Hessam Mahdavifar, Nasser Aldaghri","submitted_at":"2021-10-28T16:08:18Z","abstract_excerpt":"Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local. Models trained using FL may still leak private client information through model updates during training. Differential privacy (DP) may be employed on model updates to provide privacy guarantees within FL, typically at the cost of degraded performance of the final trained model. Both non-private FL and DP-FL can be solved using variants of the federated averaging (FedAvg) algorithm. In this work, we consider a heterogeneous DP setup where clients require var"},"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":"2110.15252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-28T16:08:18Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"15a1853c2a002d00897c8eb89c0ad3b0208bac899bf9cbbef5b3037248811a0f","abstract_canon_sha256":"97f095ac21efe7144a476b8f3f71f5c48b19aee7de28517475d20b5d37e84b61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:06.900446Z","signature_b64":"3ZJNHV4bYdcF7tdl1uVdeJXIVCTPc0d86VQRdiDG+O6CFTx3KnLeimzQokHgo9PI4EL0y5r49/LQz+GCF2fHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"363925f53d370219a8e719c2490d0e235aba08edd12ff8dbf1e7cbf5c956b6ef","last_reissued_at":"2026-07-05T05:33:06.899959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:06.899959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Heterogeneous Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ahmad Beirami, Hessam Mahdavifar, Nasser Aldaghri","submitted_at":"2021-10-28T16:08:18Z","abstract_excerpt":"Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local. Models trained using FL may still leak private client information through model updates during training. Differential privacy (DP) may be employed on model updates to provide privacy guarantees within FL, typically at the cost of degraded performance of the final trained model. Both non-private FL and DP-FL can be solved using variants of the federated averaging (FedAvg) algorithm. In this work, we consider a heterogeneous DP setup where clients require var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15252","kind":"arxiv","version":2},"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/2110.15252/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":"2110.15252","created_at":"2026-07-05T05:33:06.900017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15252v2","created_at":"2026-07-05T05:33:06.900017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15252","created_at":"2026-07-05T05:33:06.900017+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY4SL5J5G4BB","created_at":"2026-07-05T05:33:06.900017+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY4SL5J5G4BBTKHH","created_at":"2026-07-05T05:33:06.900017+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY4SL5J5","created_at":"2026-07-05T05:33:06.900017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN","json":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN.json","graph_json":"https://pith.science/api/pith-number/GY4SL5J5G4BBTKHHDHBESDIOEN/graph.json","events_json":"https://pith.science/api/pith-number/GY4SL5J5G4BBTKHHDHBESDIOEN/events.json","paper":"https://pith.science/paper/GY4SL5J5"},"agent_actions":{"view_html":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN","download_json":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN.json","view_paper":"https://pith.science/paper/GY4SL5J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15252&json=true","fetch_graph":"https://pith.science/api/pith-number/GY4SL5J5G4BBTKHHDHBESDIOEN/graph.json","fetch_events":"https://pith.science/api/pith-number/GY4SL5J5G4BBTKHHDHBESDIOEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN/action/storage_attestation","attest_author":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN/action/author_attestation","sign_citation":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN/action/citation_signature","submit_replication":"https://pith.science/pith/GY4SL5J5G4BBTKHHDHBESDIOEN/action/replication_record"}},"created_at":"2026-07-05T05:33:06.900017+00:00","updated_at":"2026-07-05T05:33:06.900017+00:00"}