{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCLUUDKKJAIKCGTNJITICL3R25","short_pith_number":"pith:XCLUUDKK","schema_version":"1.0","canonical_sha256":"b8974a0d4a4810a11a6d4a26812f71d77395516aa79a1893e1712bd1396c65d2","source":{"kind":"arxiv","id":"2401.13236","version":2},"attestation_state":"computed","paper":{"title":"How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Marios Kountouris, Yuchang Sun","submitted_at":"2024-01-24T05:41:34Z","abstract_excerpt":"Federated learning (FL) has attracted vivid attention as a privacy-preserving distributed learning framework. In this work, we focus on cross-silo FL, where clients become the model owners after training and are only concerned about the model's generalization performance on their local data. Due to the data heterogeneity issue, asking all the clients to join a single FL training process may result in model performance degradation. To investigate the effectiveness of collaboration, we first derive a generalization bound for each client when collaborating with others or when training independent"},"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":"2401.13236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-24T05:41:34Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"58234e23240bceea9c914fee6cb1401b1075fbadb81618fc1f75bcb49b46004c","abstract_canon_sha256":"b951cd6d574f05b44aa9a7190a2bdd5ae418281ac5fd2ffc4d42c5e36d47755d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:31.474651Z","signature_b64":"hnQN0BWST0dfPQN/8S3vcxgXr+veasT2JHjIcdumMBYxQij487HxwPljLwuLPTygIonN+ZymNC8y2dEcAUtcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8974a0d4a4810a11a6d4a26812f71d77395516aa79a1893e1712bd1396c65d2","last_reissued_at":"2026-07-05T09:41:31.474176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:31.474176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Marios Kountouris, Yuchang Sun","submitted_at":"2024-01-24T05:41:34Z","abstract_excerpt":"Federated learning (FL) has attracted vivid attention as a privacy-preserving distributed learning framework. In this work, we focus on cross-silo FL, where clients become the model owners after training and are only concerned about the model's generalization performance on their local data. Due to the data heterogeneity issue, asking all the clients to join a single FL training process may result in model performance degradation. To investigate the effectiveness of collaboration, we first derive a generalization bound for each client when collaborating with others or when training independent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13236","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/2401.13236/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":"2401.13236","created_at":"2026-07-05T09:41:31.474233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13236v2","created_at":"2026-07-05T09:41:31.474233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13236","created_at":"2026-07-05T09:41:31.474233+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCLUUDKKJAIK","created_at":"2026-07-05T09:41:31.474233+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCLUUDKKJAIKCGTN","created_at":"2026-07-05T09:41:31.474233+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCLUUDKK","created_at":"2026-07-05T09:41:31.474233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09822","citing_title":"pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25","json":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25.json","graph_json":"https://pith.science/api/pith-number/XCLUUDKKJAIKCGTNJITICL3R25/graph.json","events_json":"https://pith.science/api/pith-number/XCLUUDKKJAIKCGTNJITICL3R25/events.json","paper":"https://pith.science/paper/XCLUUDKK"},"agent_actions":{"view_html":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25","download_json":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25.json","view_paper":"https://pith.science/paper/XCLUUDKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13236&json=true","fetch_graph":"https://pith.science/api/pith-number/XCLUUDKKJAIKCGTNJITICL3R25/graph.json","fetch_events":"https://pith.science/api/pith-number/XCLUUDKKJAIKCGTNJITICL3R25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25/action/storage_attestation","attest_author":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25/action/author_attestation","sign_citation":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25/action/citation_signature","submit_replication":"https://pith.science/pith/XCLUUDKKJAIKCGTNJITICL3R25/action/replication_record"}},"created_at":"2026-07-05T09:41:31.474233+00:00","updated_at":"2026-07-05T09:41:31.474233+00:00"}