{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NJJ3JCA2V7DG4RFIMV6FGCNFST","short_pith_number":"pith:NJJ3JCA2","schema_version":"1.0","canonical_sha256":"6a53b4881aafc66e44a8657c5309a594fb6ba9f13989439782e70727cd71600e","source":{"kind":"arxiv","id":"2305.18285","version":1},"attestation_state":"computed","paper":{"title":"Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Gorbunov, Konstantin Mishchenko, Rustem Islamov, Samuel Horv\\'ath","submitted_at":"2023-05-29T17:54:50Z","abstract_excerpt":"We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training. In our framework, we split the variables into global parameters, which are shared across all clients, and individual local parameters, which are kept private. We prove that under the right split of parameters, it is possible to find global parameters that allow each client to fit their data perfectly, and refer to the obtained problem as overpersonalized. For instance, the shared global parameters can be used to lea"},"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":"2305.18285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T17:54:50Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"ff2e68bf50d2643e18cc0cda07a0475cce48f85db9f2f10a8fb45ab16e275c55","abstract_canon_sha256":"ad0ed7bc17b60d41c51fad619234f7489c9b7b602a97c951f3ea5a271eb9b392"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:54.655637Z","signature_b64":"OhMiWd6K8Yui/0fTBBOrRN2J/46/KP7dNvrNku7CtctJQqFShoDO2P0BQnAdRnQM87wA5fh4N4NpHJWyyyFZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a53b4881aafc66e44a8657c5309a594fb6ba9f13989439782e70727cd71600e","last_reissued_at":"2026-07-05T06:14:54.655192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:54.655192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Gorbunov, Konstantin Mishchenko, Rustem Islamov, Samuel Horv\\'ath","submitted_at":"2023-05-29T17:54:50Z","abstract_excerpt":"We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training. In our framework, we split the variables into global parameters, which are shared across all clients, and individual local parameters, which are kept private. We prove that under the right split of parameters, it is possible to find global parameters that allow each client to fit their data perfectly, and refer to the obtained problem as overpersonalized. For instance, the shared global parameters can be used to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18285","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/2305.18285/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":"2305.18285","created_at":"2026-07-05T06:14:54.655242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18285v1","created_at":"2026-07-05T06:14:54.655242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18285","created_at":"2026-07-05T06:14:54.655242+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJJ3JCA2V7DG","created_at":"2026-07-05T06:14:54.655242+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJJ3JCA2V7DG4RFI","created_at":"2026-07-05T06:14:54.655242+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJJ3JCA2","created_at":"2026-07-05T06:14:54.655242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00980","citing_title":"Incentivizing Truthful Collaboration in Heterogeneous Federated Learning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST","json":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST.json","graph_json":"https://pith.science/api/pith-number/NJJ3JCA2V7DG4RFIMV6FGCNFST/graph.json","events_json":"https://pith.science/api/pith-number/NJJ3JCA2V7DG4RFIMV6FGCNFST/events.json","paper":"https://pith.science/paper/NJJ3JCA2"},"agent_actions":{"view_html":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST","download_json":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST.json","view_paper":"https://pith.science/paper/NJJ3JCA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18285&json=true","fetch_graph":"https://pith.science/api/pith-number/NJJ3JCA2V7DG4RFIMV6FGCNFST/graph.json","fetch_events":"https://pith.science/api/pith-number/NJJ3JCA2V7DG4RFIMV6FGCNFST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST/action/storage_attestation","attest_author":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST/action/author_attestation","sign_citation":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST/action/citation_signature","submit_replication":"https://pith.science/pith/NJJ3JCA2V7DG4RFIMV6FGCNFST/action/replication_record"}},"created_at":"2026-07-05T06:14:54.655242+00:00","updated_at":"2026-07-05T06:14:54.655242+00:00"}