{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6J2NSKZ2WRMU53P7BAC2K6UHXN","short_pith_number":"pith:6J2NSKZ2","schema_version":"1.0","canonical_sha256":"f274d92b3ab4594eedff0805a57a87bb45783f6753078e1ed122602bcbb266aa","source":{"kind":"arxiv","id":"2203.11751","version":1},"attestation_state":"computed","paper":{"title":"FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng-zhong Xu, Huazhu Fu, Liang Gao, Li Li, Ming Xu, Yingwen Chen","submitted_at":"2022-03-22T14:06:26Z","abstract_excerpt":"Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. However, the key challenge in federated learning is that the clients have significant statistical heterogeneity among their local data distributions, which would cause inconsistent optimized local models on the client-side. To address this fundamental dilemma, we propose a novel federated learning algorithm with local drift decoupling and correction (FedDC). Our FedDC only introduces lightweight modifications in the local training phase, in which each client"},"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":"2203.11751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-22T14:06:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d5f559ec0fbbc73963109d14cb2657f60624e35e9158bc0729ab45dabdf8f01","abstract_canon_sha256":"e89487b95e8f494afbeb9eb21fb29844ec9d62cdc23f08aacde8ac9e70971806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:32.499703Z","signature_b64":"064RqCtZn9y19GIHTCbNgg5/nWHnyTme6xx9JNemIYhrYdiv3ln1lb6Mnl/GQtbverneuexxHgTfIh4EpBfJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f274d92b3ab4594eedff0805a57a87bb45783f6753078e1ed122602bcbb266aa","last_reissued_at":"2026-07-05T04:07:32.499214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:32.499214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng-zhong Xu, Huazhu Fu, Liang Gao, Li Li, Ming Xu, Yingwen Chen","submitted_at":"2022-03-22T14:06:26Z","abstract_excerpt":"Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. However, the key challenge in federated learning is that the clients have significant statistical heterogeneity among their local data distributions, which would cause inconsistent optimized local models on the client-side. To address this fundamental dilemma, we propose a novel federated learning algorithm with local drift decoupling and correction (FedDC). Our FedDC only introduces lightweight modifications in the local training phase, in which each client"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11751","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/2203.11751/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":"2203.11751","created_at":"2026-07-05T04:07:32.499270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11751v1","created_at":"2026-07-05T04:07:32.499270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11751","created_at":"2026-07-05T04:07:32.499270+00:00"},{"alias_kind":"pith_short_12","alias_value":"6J2NSKZ2WRMU","created_at":"2026-07-05T04:07:32.499270+00:00"},{"alias_kind":"pith_short_16","alias_value":"6J2NSKZ2WRMU53P7","created_at":"2026-07-05T04:07:32.499270+00:00"},{"alias_kind":"pith_short_8","alias_value":"6J2NSKZ2","created_at":"2026-07-05T04:07:32.499270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12768","citing_title":"Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN","json":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN.json","graph_json":"https://pith.science/api/pith-number/6J2NSKZ2WRMU53P7BAC2K6UHXN/graph.json","events_json":"https://pith.science/api/pith-number/6J2NSKZ2WRMU53P7BAC2K6UHXN/events.json","paper":"https://pith.science/paper/6J2NSKZ2"},"agent_actions":{"view_html":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN","download_json":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN.json","view_paper":"https://pith.science/paper/6J2NSKZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11751&json=true","fetch_graph":"https://pith.science/api/pith-number/6J2NSKZ2WRMU53P7BAC2K6UHXN/graph.json","fetch_events":"https://pith.science/api/pith-number/6J2NSKZ2WRMU53P7BAC2K6UHXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN/action/storage_attestation","attest_author":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN/action/author_attestation","sign_citation":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN/action/citation_signature","submit_replication":"https://pith.science/pith/6J2NSKZ2WRMU53P7BAC2K6UHXN/action/replication_record"}},"created_at":"2026-07-05T04:07:32.499270+00:00","updated_at":"2026-07-05T04:07:32.499270+00:00"}