{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PKDWAVUPWSYLJH5FCEZXHW4ZL3","short_pith_number":"pith:PKDWAVUP","schema_version":"1.0","canonical_sha256":"7a8760568fb4b0b49fa5113373db995ee34d0dbda58f78873308010af6c6f6f3","source":{"kind":"arxiv","id":"2206.07977","version":1},"attestation_state":"computed","paper":{"title":"Personalized Federated Learning via Variational Bayesian Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyang Guo, Wenpeng Li, Xu Zhang, Yinchuan Li, Yunfeng Shao","submitted_at":"2022-06-16T07:37:02Z","abstract_excerpt":"Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian variational inference named pFedBayes. To alleviate the overfitting, weight uncertainty is introduced to neural networks for clients and the server. To achieve personalization, each client updates its local distribution parameters by balancing its construction error over private data and its KL divergence with global distribution from the server. Theoretical a"},"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":"2206.07977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T07:37:02Z","cross_cats_sorted":[],"title_canon_sha256":"1ecd2eead9e716b72c1d3538ed2b74d2865be097eb0735cb41edcc07919add5b","abstract_canon_sha256":"399a63052020c26e308a50faacbe7ef4427fee540a903f8faddd92ced53a670a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:20.834261Z","signature_b64":"10mY+dMZDuEp9LDfyN10UI7/KcPIEki+pBWk97JAIx6CmOpZaYNGcYcRjZKajBaMaPa2sanua56bY00+4sOLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a8760568fb4b0b49fa5113373db995ee34d0dbda58f78873308010af6c6f6f3","last_reissued_at":"2026-07-05T04:32:20.833805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:20.833805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Federated Learning via Variational Bayesian Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyang Guo, Wenpeng Li, Xu Zhang, Yinchuan Li, Yunfeng Shao","submitted_at":"2022-06-16T07:37:02Z","abstract_excerpt":"Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian variational inference named pFedBayes. To alleviate the overfitting, weight uncertainty is introduced to neural networks for clients and the server. To achieve personalization, each client updates its local distribution parameters by balancing its construction error over private data and its KL divergence with global distribution from the server. Theoretical a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07977","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/2206.07977/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":"2206.07977","created_at":"2026-07-05T04:32:20.833864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07977v1","created_at":"2026-07-05T04:32:20.833864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07977","created_at":"2026-07-05T04:32:20.833864+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKDWAVUPWSYL","created_at":"2026-07-05T04:32:20.833864+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKDWAVUPWSYLJH5F","created_at":"2026-07-05T04:32:20.833864+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKDWAVUP","created_at":"2026-07-05T04:32:20.833864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10521","citing_title":"Variational Gaussian Mixture Manifold Models for Client-Specific Federated Personalization","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3","json":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3.json","graph_json":"https://pith.science/api/pith-number/PKDWAVUPWSYLJH5FCEZXHW4ZL3/graph.json","events_json":"https://pith.science/api/pith-number/PKDWAVUPWSYLJH5FCEZXHW4ZL3/events.json","paper":"https://pith.science/paper/PKDWAVUP"},"agent_actions":{"view_html":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3","download_json":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3.json","view_paper":"https://pith.science/paper/PKDWAVUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07977&json=true","fetch_graph":"https://pith.science/api/pith-number/PKDWAVUPWSYLJH5FCEZXHW4ZL3/graph.json","fetch_events":"https://pith.science/api/pith-number/PKDWAVUPWSYLJH5FCEZXHW4ZL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3/action/storage_attestation","attest_author":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3/action/author_attestation","sign_citation":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3/action/citation_signature","submit_replication":"https://pith.science/pith/PKDWAVUPWSYLJH5FCEZXHW4ZL3/action/replication_record"}},"created_at":"2026-07-05T04:32:20.833864+00:00","updated_at":"2026-07-05T04:32:20.833864+00:00"}