{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FYODRMOHMLU3N4722NWCRDMCGY","short_pith_number":"pith:FYODRMOH","schema_version":"1.0","canonical_sha256":"2e1c38b1c762e9b6f3fad36c288d823605bc659719348e7fe37971f9180fddb1","source":{"kind":"arxiv","id":"2106.15482","version":2},"attestation_state":"computed","paper":{"title":"Personalized Federated Learning with Gaussian Processes","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Idan Achituve","submitted_at":"2021-06-29T15:09:13Z","abstract_excerpt":"Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. Personalized federated learning (PFL) further extends this setup to handle data heterogeneity between clients by learning personalized models. A key challenge in this setting is to learn effectively across clients even though each client has unique data that is often limited in size. Here we present pFedGP, a solution to PFL that is based on Gaussian processes (GPs) with deep kernel learning. GPs are highly expressive models that work well in the low data regime due to "},"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":"2106.15482","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T15:09:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"902b191f3cd4ed60f31d9677133691cee7e89cd7d8c56f2c88e89aba11fdc27c","abstract_canon_sha256":"1138bf4e30f25fe18c8a22bcc478944181f8d42056fd8457ca630d3c786b07fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:32.663778Z","signature_b64":"LARsLw3LHcUeq3K15vDDTEvBYyZgTVkGQHikCb3DJDjXj/CNMGfbCotBhKmN8aYFkrajbcmjYoNV/hQvWHwVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e1c38b1c762e9b6f3fad36c288d823605bc659719348e7fe37971f9180fddb1","last_reissued_at":"2026-07-05T03:25:32.663251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:32.663251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Federated Learning with Gaussian Processes","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Idan Achituve","submitted_at":"2021-06-29T15:09:13Z","abstract_excerpt":"Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. Personalized federated learning (PFL) further extends this setup to handle data heterogeneity between clients by learning personalized models. A key challenge in this setting is to learn effectively across clients even though each client has unique data that is often limited in size. Here we present pFedGP, a solution to PFL that is based on Gaussian processes (GPs) with deep kernel learning. GPs are highly expressive models that work well in the low data regime due to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15482","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/2106.15482/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":"2106.15482","created_at":"2026-07-05T03:25:32.663312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15482v2","created_at":"2026-07-05T03:25:32.663312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15482","created_at":"2026-07-05T03:25:32.663312+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYODRMOHMLU3","created_at":"2026-07-05T03:25:32.663312+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYODRMOHMLU3N472","created_at":"2026-07-05T03:25:32.663312+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYODRMOH","created_at":"2026-07-05T03:25:32.663312+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/FYODRMOHMLU3N4722NWCRDMCGY","json":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY.json","graph_json":"https://pith.science/api/pith-number/FYODRMOHMLU3N4722NWCRDMCGY/graph.json","events_json":"https://pith.science/api/pith-number/FYODRMOHMLU3N4722NWCRDMCGY/events.json","paper":"https://pith.science/paper/FYODRMOH"},"agent_actions":{"view_html":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY","download_json":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY.json","view_paper":"https://pith.science/paper/FYODRMOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15482&json=true","fetch_graph":"https://pith.science/api/pith-number/FYODRMOHMLU3N4722NWCRDMCGY/graph.json","fetch_events":"https://pith.science/api/pith-number/FYODRMOHMLU3N4722NWCRDMCGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY/action/storage_attestation","attest_author":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY/action/author_attestation","sign_citation":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY/action/citation_signature","submit_replication":"https://pith.science/pith/FYODRMOHMLU3N4722NWCRDMCGY/action/replication_record"}},"created_at":"2026-07-05T03:25:32.663312+00:00","updated_at":"2026-07-05T03:25:32.663312+00:00"}