{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6RAOYQZVVSZRNF34DHOPKTJPKJ","short_pith_number":"pith:6RAOYQZV","schema_version":"1.0","canonical_sha256":"f440ec4335acb316977c19dcf54d2f5259ce98ec2ee953254fda54d8041b3e9b","source":{"kind":"arxiv","id":"2302.11051","version":1},"attestation_state":"computed","paper":{"title":"Fusion of Global and Local Knowledge for Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Tiansheng Huang, Weiwei Lin, Yan Sun","submitted_at":"2023-02-21T23:09:45Z","abstract_excerpt":"Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data. However, it is still inconclusive about how to design personalized models with better representation of shared global knowledge and personalized pattern. To bridge the gap, we in this paper explore personalized models with low-rank and sparse decomposition. Specifically, we employ proper regularization to extract a low-rank global knowledge representation (GKR), so as to distill global knowledge into a compact representation. Subsequently, we e"},"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":"2302.11051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T23:09:45Z","cross_cats_sorted":[],"title_canon_sha256":"5d780a11b6a454f1678c5d05fb4d125b819a27b949be3741f8c11f7a7124737c","abstract_canon_sha256":"494d0d4a9fdc66adcd5ab27bc88b2417cf8179049880ded63bab7f08ea4e1499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:29.906285Z","signature_b64":"xRQFGnkZInA4LzlLdncEy9iUgRKNflWlCLm9qme25qtXfaojkxohv0YhZwim8oloBX+KblwUD1ywmRKhexDaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f440ec4335acb316977c19dcf54d2f5259ce98ec2ee953254fda54d8041b3e9b","last_reissued_at":"2026-07-05T05:44:29.905817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:29.905817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusion of Global and Local Knowledge for Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Tiansheng Huang, Weiwei Lin, Yan Sun","submitted_at":"2023-02-21T23:09:45Z","abstract_excerpt":"Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data. However, it is still inconclusive about how to design personalized models with better representation of shared global knowledge and personalized pattern. To bridge the gap, we in this paper explore personalized models with low-rank and sparse decomposition. Specifically, we employ proper regularization to extract a low-rank global knowledge representation (GKR), so as to distill global knowledge into a compact representation. Subsequently, we e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11051","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/2302.11051/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":"2302.11051","created_at":"2026-07-05T05:44:29.905874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11051v1","created_at":"2026-07-05T05:44:29.905874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11051","created_at":"2026-07-05T05:44:29.905874+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RAOYQZVVSZR","created_at":"2026-07-05T05:44:29.905874+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RAOYQZVVSZRNF34","created_at":"2026-07-05T05:44:29.905874+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RAOYQZV","created_at":"2026-07-05T05:44:29.905874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12768","citing_title":"Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ","json":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ.json","graph_json":"https://pith.science/api/pith-number/6RAOYQZVVSZRNF34DHOPKTJPKJ/graph.json","events_json":"https://pith.science/api/pith-number/6RAOYQZVVSZRNF34DHOPKTJPKJ/events.json","paper":"https://pith.science/paper/6RAOYQZV"},"agent_actions":{"view_html":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ","download_json":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ.json","view_paper":"https://pith.science/paper/6RAOYQZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11051&json=true","fetch_graph":"https://pith.science/api/pith-number/6RAOYQZVVSZRNF34DHOPKTJPKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6RAOYQZVVSZRNF34DHOPKTJPKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ/action/storage_attestation","attest_author":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ/action/author_attestation","sign_citation":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ/action/citation_signature","submit_replication":"https://pith.science/pith/6RAOYQZVVSZRNF34DHOPKTJPKJ/action/replication_record"}},"created_at":"2026-07-05T05:44:29.905874+00:00","updated_at":"2026-07-05T05:44:29.905874+00:00"}