{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W7YFZPAMZAM3CJI3JSCVHCQYDM","short_pith_number":"pith:W7YFZPAM","schema_version":"1.0","canonical_sha256":"b7f05cbc0cc819b1251b4c85538a181b39f242b7d1595558a30e1cdc50690307","source":{"kind":"arxiv","id":"2605.21264","version":1},"attestation_state":"computed","paper":{"title":"FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fulian Li, Junhua Wang, Lixin Duan, Penglin Dai, Xiao Wu, Xincao Xu","submitted_at":"2026-05-20T14:52:07Z","abstract_excerpt":"Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental challenge. Traditional averaging-based approaches suffer from parameter divergence under non-IID conditions, while personalized FL methods overfit to local data and fail to generalize to new clients (cold-start problem). Mixture-of-Experts naturally addresses this by routing heterogeneous data to specialized experts rather than forcing uniform aggregation. In this paper, we propose FedCoE, a Federated Coordinated dual-level mixture-of-Experts "},"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":"2605.21264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"397a20341ddce34b10f051f10ff99e7d5584dbd8d07ab73fbecdb60222e0bf50","abstract_canon_sha256":"75f6021c2098a9c73b00f5870c1bd596c93ba1b2150e8ddb6a88b3d6411efb32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:25.666966Z","signature_b64":"MMAerS9gzVQqt7oUcljfnbC8e8T1xsyUo4r6PzUT7Uh1kCDIF2RMWyZJ/e7UgNvZ206cBHMq5jk6njurGMzOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7f05cbc0cc819b1251b4c85538a181b39f242b7d1595558a30e1cdc50690307","last_reissued_at":"2026-05-21T02:05:25.666109Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:25.666109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fulian Li, Junhua Wang, Lixin Duan, Penglin Dai, Xiao Wu, Xincao Xu","submitted_at":"2026-05-20T14:52:07Z","abstract_excerpt":"Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental challenge. Traditional averaging-based approaches suffer from parameter divergence under non-IID conditions, while personalized FL methods overfit to local data and fail to generalize to new clients (cold-start problem). Mixture-of-Experts naturally addresses this by routing heterogeneous data to specialized experts rather than forcing uniform aggregation. In this paper, we propose FedCoE, a Federated Coordinated dual-level mixture-of-Experts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21264","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/2605.21264/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":"2605.21264","created_at":"2026-05-21T02:05:25.666256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21264v1","created_at":"2026-05-21T02:05:25.666256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21264","created_at":"2026-05-21T02:05:25.666256+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7YFZPAMZAM3","created_at":"2026-05-21T02:05:25.666256+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7YFZPAMZAM3CJI3","created_at":"2026-05-21T02:05:25.666256+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7YFZPAM","created_at":"2026-05-21T02:05:25.666256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM","json":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM.json","graph_json":"https://pith.science/api/pith-number/W7YFZPAMZAM3CJI3JSCVHCQYDM/graph.json","events_json":"https://pith.science/api/pith-number/W7YFZPAMZAM3CJI3JSCVHCQYDM/events.json","paper":"https://pith.science/paper/W7YFZPAM"},"agent_actions":{"view_html":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM","download_json":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM.json","view_paper":"https://pith.science/paper/W7YFZPAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21264&json=true","fetch_graph":"https://pith.science/api/pith-number/W7YFZPAMZAM3CJI3JSCVHCQYDM/graph.json","fetch_events":"https://pith.science/api/pith-number/W7YFZPAMZAM3CJI3JSCVHCQYDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM/action/storage_attestation","attest_author":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM/action/author_attestation","sign_citation":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM/action/citation_signature","submit_replication":"https://pith.science/pith/W7YFZPAMZAM3CJI3JSCVHCQYDM/action/replication_record"}},"created_at":"2026-05-21T02:05:25.666256+00:00","updated_at":"2026-05-21T02:05:25.666256+00:00"}