{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YIKJ7P7SWRRPXE6PPP76S5WT2I","short_pith_number":"pith:YIKJ7P7S","schema_version":"1.0","canonical_sha256":"c2149fbff2b462fb93cf7bffe976d3d20e73f5c8907ce81f84abccb54371085a","source":{"kind":"arxiv","id":"2105.15191","version":1},"attestation_state":"computed","paper":{"title":"Unifying Distillation with Personalization in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Berkay Celik, Habiba Farrukh, Siddharth Divi","submitted_at":"2021-05-31T17:54:29Z","abstract_excerpt":"Federated learning (FL) is a decentralized privacy-preserving learning technique in which clients learn a joint collaborative model through a central aggregator without sharing their data. In this setting, all clients learn a single common predictor (FedAvg), which does not generalize well on each client's local data due to the statistical data heterogeneity among clients. In this paper, we address this problem with PersFL, a discrete two-stage personalized learning algorithm. In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase. In the second "},"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":"2105.15191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-31T17:54:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5dc5ce68caf44abf4c119681fa6464025b9ec09141ae42f233ffc15276e744e4","abstract_canon_sha256":"243f87007103b7adf3b4ee399405523d6e37627cb94b63f969a10462b62e14a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:45.809564Z","signature_b64":"9clbji3kLPkIsvP8kW+AyqiLNZ5wXLoskjRTxD9mz7VCd3lpjbHFNchjEofpAxQrlBhUyFlPdtHTHbdtHxh/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2149fbff2b462fb93cf7bffe976d3d20e73f5c8907ce81f84abccb54371085a","last_reissued_at":"2026-07-05T02:44:45.809116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:45.809116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Distillation with Personalization in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Berkay Celik, Habiba Farrukh, Siddharth Divi","submitted_at":"2021-05-31T17:54:29Z","abstract_excerpt":"Federated learning (FL) is a decentralized privacy-preserving learning technique in which clients learn a joint collaborative model through a central aggregator without sharing their data. In this setting, all clients learn a single common predictor (FedAvg), which does not generalize well on each client's local data due to the statistical data heterogeneity among clients. In this paper, we address this problem with PersFL, a discrete two-stage personalized learning algorithm. In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase. In the second "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.15191","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/2105.15191/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":"2105.15191","created_at":"2026-07-05T02:44:45.809175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.15191v1","created_at":"2026-07-05T02:44:45.809175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.15191","created_at":"2026-07-05T02:44:45.809175+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIKJ7P7SWRRP","created_at":"2026-07-05T02:44:45.809175+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIKJ7P7SWRRPXE6P","created_at":"2026-07-05T02:44:45.809175+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIKJ7P7S","created_at":"2026-07-05T02:44:45.809175+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/YIKJ7P7SWRRPXE6PPP76S5WT2I","json":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I.json","graph_json":"https://pith.science/api/pith-number/YIKJ7P7SWRRPXE6PPP76S5WT2I/graph.json","events_json":"https://pith.science/api/pith-number/YIKJ7P7SWRRPXE6PPP76S5WT2I/events.json","paper":"https://pith.science/paper/YIKJ7P7S"},"agent_actions":{"view_html":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I","download_json":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I.json","view_paper":"https://pith.science/paper/YIKJ7P7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.15191&json=true","fetch_graph":"https://pith.science/api/pith-number/YIKJ7P7SWRRPXE6PPP76S5WT2I/graph.json","fetch_events":"https://pith.science/api/pith-number/YIKJ7P7SWRRPXE6PPP76S5WT2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I/action/storage_attestation","attest_author":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I/action/author_attestation","sign_citation":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I/action/citation_signature","submit_replication":"https://pith.science/pith/YIKJ7P7SWRRPXE6PPP76S5WT2I/action/replication_record"}},"created_at":"2026-07-05T02:44:45.809175+00:00","updated_at":"2026-07-05T02:44:45.809175+00:00"}