{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BG3D46SLS5GANW4MPESGWSOQJL","short_pith_number":"pith:BG3D46SL","schema_version":"1.0","canonical_sha256":"09b63e7a4b974c06db8c79246b49d04ae5681a8c8085573f6a2bd3e63c0b50cc","source":{"kind":"arxiv","id":"1910.08234","version":3},"attestation_state":"computed","paper":{"title":"Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lifeng Sun, Rui-Xiao Zhang, Ruiyu Li, Tianchi Huang, Xin Yao","submitted_at":"2019-10-18T03:17:22Z","abstract_excerpt":"Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and privacy concerns brought by transmitting raw data. However, through theoretical analysis we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the expected target distribution and the optimization objectives"},"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":"1910.08234","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T03:17:22Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"0e40091721e7153911c2299a7a82af5b9fdb4ff5ae531c596e8ed8870b21dfae","abstract_canon_sha256":"b441e1943ee6b218e9d294d6776084ccf43e8bf8694c1bfec2e8636c0c2dbf7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:54.307902Z","signature_b64":"qnjC31nnQGXolXLtdYKzwEl2jIv+MGXBRaHFaGpqNaAE6xm2a0YlPdjPgBbTDOXPBf03/bLUWW2EPGlKNAv1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b63e7a4b974c06db8c79246b49d04ae5681a8c8085573f6a2bd3e63c0b50cc","last_reissued_at":"2026-07-05T01:59:54.307520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:54.307520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lifeng Sun, Rui-Xiao Zhang, Ruiyu Li, Tianchi Huang, Xin Yao","submitted_at":"2019-10-18T03:17:22Z","abstract_excerpt":"Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and privacy concerns brought by transmitting raw data. However, through theoretical analysis we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the expected target distribution and the optimization objectives"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08234","kind":"arxiv","version":3},"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/1910.08234/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":"1910.08234","created_at":"2026-07-05T01:59:54.307577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.08234v3","created_at":"2026-07-05T01:59:54.307577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08234","created_at":"2026-07-05T01:59:54.307577+00:00"},{"alias_kind":"pith_short_12","alias_value":"BG3D46SLS5GA","created_at":"2026-07-05T01:59:54.307577+00:00"},{"alias_kind":"pith_short_16","alias_value":"BG3D46SLS5GANW4M","created_at":"2026-07-05T01:59:54.307577+00:00"},{"alias_kind":"pith_short_8","alias_value":"BG3D46SL","created_at":"2026-07-05T01:59:54.307577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14539","citing_title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL","json":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL.json","graph_json":"https://pith.science/api/pith-number/BG3D46SLS5GANW4MPESGWSOQJL/graph.json","events_json":"https://pith.science/api/pith-number/BG3D46SLS5GANW4MPESGWSOQJL/events.json","paper":"https://pith.science/paper/BG3D46SL"},"agent_actions":{"view_html":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL","download_json":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL.json","view_paper":"https://pith.science/paper/BG3D46SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.08234&json=true","fetch_graph":"https://pith.science/api/pith-number/BG3D46SLS5GANW4MPESGWSOQJL/graph.json","fetch_events":"https://pith.science/api/pith-number/BG3D46SLS5GANW4MPESGWSOQJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL/action/storage_attestation","attest_author":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL/action/author_attestation","sign_citation":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL/action/citation_signature","submit_replication":"https://pith.science/pith/BG3D46SLS5GANW4MPESGWSOQJL/action/replication_record"}},"created_at":"2026-07-05T01:59:54.307577+00:00","updated_at":"2026-07-05T01:59:54.307577+00:00"}