{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RTGD2VJSWYFXHXAZQT43OCJJV7","short_pith_number":"pith:RTGD2VJS","schema_version":"1.0","canonical_sha256":"8ccc3d5532b60b73dc1984f9b70929afefb81c68499b146209faace798d875f8","source":{"kind":"arxiv","id":"2503.07505","version":1},"attestation_state":"computed","paper":{"title":"From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jun Pang, Qiongxiu Li, Wenrui Yu, Yufei Xia","submitted_at":"2025-03-10T16:27:40Z","abstract_excerpt":"Federated Learning (FL) enables collaborative learning without directly sharing individual's raw data. FL can be implemented in either a centralized (server-based) or decentralized (peer-to-peer) manner. In this survey, we present a novel perspective: the fundamental difference between centralized FL (CFL) and decentralized FL (DFL) is not merely the network topology, but the underlying training protocol: separate aggregation vs. joint optimization. We argue that this distinction in protocol leads to significant differences in model utility, privacy preservation, and robustness to attacks. We "},"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":"2503.07505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T16:27:40Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"f03986065308a040ebc07349674e6b7a56e715cee9997338315d45b81db0e321","abstract_canon_sha256":"13bdc19596c53789b3574595b8f29b7bdff29b3ff202a0243798cde664275f72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:57.738727Z","signature_b64":"6UtUqbC6eY6huJ/4MXPjmw57zTBFOuIx10RISCIvMd24rvxuDhbVTdWYP6YH0uysLHqwBqe4+sD9tkH4+/R8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ccc3d5532b60b73dc1984f9b70929afefb81c68499b146209faace798d875f8","last_reissued_at":"2026-07-05T10:27:57.738220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:57.738220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jun Pang, Qiongxiu Li, Wenrui Yu, Yufei Xia","submitted_at":"2025-03-10T16:27:40Z","abstract_excerpt":"Federated Learning (FL) enables collaborative learning without directly sharing individual's raw data. FL can be implemented in either a centralized (server-based) or decentralized (peer-to-peer) manner. In this survey, we present a novel perspective: the fundamental difference between centralized FL (CFL) and decentralized FL (DFL) is not merely the network topology, but the underlying training protocol: separate aggregation vs. joint optimization. We argue that this distinction in protocol leads to significant differences in model utility, privacy preservation, and robustness to attacks. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07505","kind":"arxiv","version":1},"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/2503.07505/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":"2503.07505","created_at":"2026-07-05T10:27:57.738279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07505v1","created_at":"2026-07-05T10:27:57.738279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07505","created_at":"2026-07-05T10:27:57.738279+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTGD2VJSWYFX","created_at":"2026-07-05T10:27:57.738279+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTGD2VJSWYFXHXAZ","created_at":"2026-07-05T10:27:57.738279+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTGD2VJS","created_at":"2026-07-05T10:27:57.738279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20031","citing_title":"Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20031","citing_title":"Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7","json":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7.json","graph_json":"https://pith.science/api/pith-number/RTGD2VJSWYFXHXAZQT43OCJJV7/graph.json","events_json":"https://pith.science/api/pith-number/RTGD2VJSWYFXHXAZQT43OCJJV7/events.json","paper":"https://pith.science/paper/RTGD2VJS"},"agent_actions":{"view_html":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7","download_json":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7.json","view_paper":"https://pith.science/paper/RTGD2VJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07505&json=true","fetch_graph":"https://pith.science/api/pith-number/RTGD2VJSWYFXHXAZQT43OCJJV7/graph.json","fetch_events":"https://pith.science/api/pith-number/RTGD2VJSWYFXHXAZQT43OCJJV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7/action/storage_attestation","attest_author":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7/action/author_attestation","sign_citation":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7/action/citation_signature","submit_replication":"https://pith.science/pith/RTGD2VJSWYFXHXAZQT43OCJJV7/action/replication_record"}},"created_at":"2026-07-05T10:27:57.738279+00:00","updated_at":"2026-07-05T10:27:57.738279+00:00"}