{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KKIW2USFFCAA3M3EMJIU4WJIHA","short_pith_number":"pith:KKIW2USF","schema_version":"1.0","canonical_sha256":"52916d524528800db36462514e5928380567bf9834f11be122130d55393e3e03","source":{"kind":"arxiv","id":"2107.10663","version":1},"attestation_state":"computed","paper":{"title":"Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fan Lai, Mosharaf Chowdhury, Naichen Shi, Raed Al Kontar","submitted_at":"2021-07-21T14:40:14Z","abstract_excerpt":"In this paper we propose Fed-ensemble: a simple approach that bringsmodel ensembling to federated learning (FL). Instead of aggregating localmodels to update a single global model, Fed-ensemble uses random permutations to update a group of K models and then obtains predictions through model averaging. Fed-ensemble can be readily utilized within established FL methods and does not impose a computational overhead as it only requires one of the K models to be sent to a client in each communication round. Theoretically, we show that predictions on newdata from all K models belong to the same predi"},"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":"2107.10663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-21T14:40:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab9cd099070c3e172cdca3fdea86343874d48e50706eb835f3163d57cfae0d09","abstract_canon_sha256":"7172d485cdaaa8f91de618c508bbd141f4589ebcdf96c15c6cf68d436ad84a0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:38.551352Z","signature_b64":"0onbz6TgfDN5o+c/TT/7oecseesFSs+E2BHuFm8YXDsszV3P8zP0LK7B5U2dPp37Ni46d1qaoauUVxGjt+F1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52916d524528800db36462514e5928380567bf9834f11be122130d55393e3e03","last_reissued_at":"2026-07-05T06:26:38.550785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:38.550785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fan Lai, Mosharaf Chowdhury, Naichen Shi, Raed Al Kontar","submitted_at":"2021-07-21T14:40:14Z","abstract_excerpt":"In this paper we propose Fed-ensemble: a simple approach that bringsmodel ensembling to federated learning (FL). Instead of aggregating localmodels to update a single global model, Fed-ensemble uses random permutations to update a group of K models and then obtains predictions through model averaging. Fed-ensemble can be readily utilized within established FL methods and does not impose a computational overhead as it only requires one of the K models to be sent to a client in each communication round. Theoretically, we show that predictions on newdata from all K models belong to the same predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10663","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/2107.10663/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":"2107.10663","created_at":"2026-07-05T06:26:38.550846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10663v1","created_at":"2026-07-05T06:26:38.550846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10663","created_at":"2026-07-05T06:26:38.550846+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKIW2USFFCAA","created_at":"2026-07-05T06:26:38.550846+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKIW2USFFCAA3M3E","created_at":"2026-07-05T06:26:38.550846+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKIW2USF","created_at":"2026-07-05T06:26:38.550846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12768","citing_title":"Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA","json":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA.json","graph_json":"https://pith.science/api/pith-number/KKIW2USFFCAA3M3EMJIU4WJIHA/graph.json","events_json":"https://pith.science/api/pith-number/KKIW2USFFCAA3M3EMJIU4WJIHA/events.json","paper":"https://pith.science/paper/KKIW2USF"},"agent_actions":{"view_html":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA","download_json":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA.json","view_paper":"https://pith.science/paper/KKIW2USF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10663&json=true","fetch_graph":"https://pith.science/api/pith-number/KKIW2USFFCAA3M3EMJIU4WJIHA/graph.json","fetch_events":"https://pith.science/api/pith-number/KKIW2USFFCAA3M3EMJIU4WJIHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA/action/storage_attestation","attest_author":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA/action/author_attestation","sign_citation":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA/action/citation_signature","submit_replication":"https://pith.science/pith/KKIW2USFFCAA3M3EMJIU4WJIHA/action/replication_record"}},"created_at":"2026-07-05T06:26:38.550846+00:00","updated_at":"2026-07-05T06:26:38.550846+00:00"}