{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YIC4T2IKW4O7ATOVJ5YDU3E5R","short_pith_number":"pith:7YIC4T2I","schema_version":"1.0","canonical_sha256":"fe102e4f4855b8ef826eaa7b81d364ec4f2fdd1efb4492e9380f48f6114a1e3b","source":{"kind":"arxiv","id":"2406.19931","version":2},"attestation_state":"computed","paper":{"title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guogang Zhu, Haolin Wang, Hao Su, Jianwei Niu, Shaojie Tang, Xinghao Wu, Xuefeng Liu","submitted_at":"2024-06-28T14:01:22Z","abstract_excerpt":"To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puz"},"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":"2406.19931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-28T14:01:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9031e1a366cbc2248beee0f5a9cb8685a8c09a5face7fb1f19ceaab26e7003f0","abstract_canon_sha256":"32925d91dcd9caf4309785bb00f97cf2764b3a28daa7161d57c85a1492003497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:10.936931Z","signature_b64":"BNCXH0NZGcE06TVIHg1TRuarvI6gYyHuzg9Wdob0g37Zq7GRfFJQAMC9LaFYIu6XzQDztAVgHZdd7qZjFzLvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe102e4f4855b8ef826eaa7b81d364ec4f2fdd1efb4492e9380f48f6114a1e3b","last_reissued_at":"2026-07-05T09:19:10.936439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:10.936439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guogang Zhu, Haolin Wang, Hao Su, Jianwei Niu, Shaojie Tang, Xinghao Wu, Xuefeng Liu","submitted_at":"2024-06-28T14:01:22Z","abstract_excerpt":"To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19931","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/2406.19931/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":"2406.19931","created_at":"2026-07-05T09:19:10.936501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19931v2","created_at":"2026-07-05T09:19:10.936501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19931","created_at":"2026-07-05T09:19:10.936501+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YIC4T2IKW4O","created_at":"2026-07-05T09:19:10.936501+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YIC4T2IKW4O7ATO","created_at":"2026-07-05T09:19:10.936501+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YIC4T2I","created_at":"2026-07-05T09:19:10.936501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03231","citing_title":"The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R","json":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R.json","graph_json":"https://pith.science/api/pith-number/7YIC4T2IKW4O7ATOVJ5YDU3E5R/graph.json","events_json":"https://pith.science/api/pith-number/7YIC4T2IKW4O7ATOVJ5YDU3E5R/events.json","paper":"https://pith.science/paper/7YIC4T2I"},"agent_actions":{"view_html":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R","download_json":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R.json","view_paper":"https://pith.science/paper/7YIC4T2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19931&json=true","fetch_graph":"https://pith.science/api/pith-number/7YIC4T2IKW4O7ATOVJ5YDU3E5R/graph.json","fetch_events":"https://pith.science/api/pith-number/7YIC4T2IKW4O7ATOVJ5YDU3E5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R/action/storage_attestation","attest_author":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R/action/author_attestation","sign_citation":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R/action/citation_signature","submit_replication":"https://pith.science/pith/7YIC4T2IKW4O7ATOVJ5YDU3E5R/action/replication_record"}},"created_at":"2026-07-05T09:19:10.936501+00:00","updated_at":"2026-07-05T09:19:10.936501+00:00"}