{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EQOWFL3SKBATA77JDYLZNCVWSY","short_pith_number":"pith:EQOWFL3S","schema_version":"1.0","canonical_sha256":"241d62af725041307fe91e17968ab6963dc7cc64505987b069dfcb900f68c516","source":{"kind":"arxiv","id":"2009.01974","version":4},"attestation_state":"computed","paper":{"title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong-You Chen, Wei-Lun Chao","submitted_at":"2020-09-04T01:18:25Z","abstract_excerpt":"Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting "},"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":"2009.01974","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-04T01:18:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a2f1434bc8f423552a99143b6402ae913279792407f3b81bedbb65d07be732f","abstract_canon_sha256":"e70d03fb1e9c82c3a9694602ee981f020ef0ce44d90932ce4d8803903ec8a246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:06.273660Z","signature_b64":"AlNjGIb4ZRPt7efLoJTQozV9F8cMI+zzxeUMv7j+kduR1aqhSPN20gW7rk49XrpapSkaLjkknIBqYLMLJlIvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241d62af725041307fe91e17968ab6963dc7cc64505987b069dfcb900f68c516","last_reissued_at":"2026-07-05T03:21:06.273210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:06.273210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong-You Chen, Wei-Lun Chao","submitted_at":"2020-09-04T01:18:25Z","abstract_excerpt":"Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01974","kind":"arxiv","version":4},"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/2009.01974/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":"2009.01974","created_at":"2026-07-05T03:21:06.273267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.01974v4","created_at":"2026-07-05T03:21:06.273267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01974","created_at":"2026-07-05T03:21:06.273267+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQOWFL3SKBAT","created_at":"2026-07-05T03:21:06.273267+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQOWFL3SKBATA77J","created_at":"2026-07-05T03:21:06.273267+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQOWFL3S","created_at":"2026-07-05T03:21:06.273267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29002","citing_title":"FedQHD: Closed-Form Function-Space Federated Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17552","citing_title":"Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13004","citing_title":"Towards Uncertainty-Aware Federated Granger Causal Learning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY","json":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY.json","graph_json":"https://pith.science/api/pith-number/EQOWFL3SKBATA77JDYLZNCVWSY/graph.json","events_json":"https://pith.science/api/pith-number/EQOWFL3SKBATA77JDYLZNCVWSY/events.json","paper":"https://pith.science/paper/EQOWFL3S"},"agent_actions":{"view_html":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY","download_json":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY.json","view_paper":"https://pith.science/paper/EQOWFL3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.01974&json=true","fetch_graph":"https://pith.science/api/pith-number/EQOWFL3SKBATA77JDYLZNCVWSY/graph.json","fetch_events":"https://pith.science/api/pith-number/EQOWFL3SKBATA77JDYLZNCVWSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY/action/storage_attestation","attest_author":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY/action/author_attestation","sign_citation":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY/action/citation_signature","submit_replication":"https://pith.science/pith/EQOWFL3SKBATA77JDYLZNCVWSY/action/replication_record"}},"created_at":"2026-07-05T03:21:06.273267+00:00","updated_at":"2026-07-05T03:21:06.273267+00:00"}