{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2NWE3QV3IDL2IF5QMZIXCXPKH2","short_pith_number":"pith:2NWE3QV3","schema_version":"1.0","canonical_sha256":"d36c4dc2bb40d7a417b06651715dea3e83d24e2caa61c9d4855116547a0f70e4","source":{"kind":"arxiv","id":"2302.10429","version":2},"attestation_state":"computed","paper":{"title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Li Shen, Tiansheng Huang, Yan Sun","submitted_at":"2023-02-21T03:55:29Z","abstract_excerpt":"Federated learning is an emerging distributed machine learning framework which jointly trains a global model via a large number of local devices with data privacy protections. Its performance suffers from the non-vanishing biases introduced by the local inconsistent optimal and the rugged client-drifts by the local over-fitting. In this paper, we propose a novel and practical method, FedSpeed, to alleviate the negative impacts posed by these problems. Concretely, FedSpeed applies the prox-correction term on the current local updates to efficiently reduce the biases introduced by the prox-term,"},"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":"2302.10429","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T03:55:29Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"53260abd500c0d8ceb129db59d5f13aab3fe3b1ccbfa64eefcd1ca1dc998d048","abstract_canon_sha256":"8a2b5dea7701b7d7ea43ac053829c07882a3ce9a6366f2a71870ac8e7debf71a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:46.128837Z","signature_b64":"Iejs4bdaD5J7tJeYlaNwgNmzlfVw4+aeZBJlO1gKsA6P7tmtXUF4vfHUwqKlt1e+h0m0ZO1DMUYJOZBNhjEpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d36c4dc2bb40d7a417b06651715dea3e83d24e2caa61c9d4855116547a0f70e4","last_reissued_at":"2026-07-05T06:27:46.128329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:46.128329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Li Shen, Tiansheng Huang, Yan Sun","submitted_at":"2023-02-21T03:55:29Z","abstract_excerpt":"Federated learning is an emerging distributed machine learning framework which jointly trains a global model via a large number of local devices with data privacy protections. Its performance suffers from the non-vanishing biases introduced by the local inconsistent optimal and the rugged client-drifts by the local over-fitting. In this paper, we propose a novel and practical method, FedSpeed, to alleviate the negative impacts posed by these problems. Concretely, FedSpeed applies the prox-correction term on the current local updates to efficiently reduce the biases introduced by the prox-term,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10429","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/2302.10429/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":"2302.10429","created_at":"2026-07-05T06:27:46.128391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10429v2","created_at":"2026-07-05T06:27:46.128391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10429","created_at":"2026-07-05T06:27:46.128391+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NWE3QV3IDL2","created_at":"2026-07-05T06:27:46.128391+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NWE3QV3IDL2IF5Q","created_at":"2026-07-05T06:27:46.128391+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NWE3QV3","created_at":"2026-07-05T06:27:46.128391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.15621","citing_title":"Convergent Differential Privacy Analysis for General Federated Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09144","citing_title":"FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2","json":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2.json","graph_json":"https://pith.science/api/pith-number/2NWE3QV3IDL2IF5QMZIXCXPKH2/graph.json","events_json":"https://pith.science/api/pith-number/2NWE3QV3IDL2IF5QMZIXCXPKH2/events.json","paper":"https://pith.science/paper/2NWE3QV3"},"agent_actions":{"view_html":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2","download_json":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2.json","view_paper":"https://pith.science/paper/2NWE3QV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10429&json=true","fetch_graph":"https://pith.science/api/pith-number/2NWE3QV3IDL2IF5QMZIXCXPKH2/graph.json","fetch_events":"https://pith.science/api/pith-number/2NWE3QV3IDL2IF5QMZIXCXPKH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2/action/storage_attestation","attest_author":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2/action/author_attestation","sign_citation":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2/action/citation_signature","submit_replication":"https://pith.science/pith/2NWE3QV3IDL2IF5QMZIXCXPKH2/action/replication_record"}},"created_at":"2026-07-05T06:27:46.128391+00:00","updated_at":"2026-07-05T06:27:46.128391+00:00"}