{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNK2OM5KOZZFN4BTAEOXLVESOJ","short_pith_number":"pith:FNK2OM5K","schema_version":"1.0","canonical_sha256":"2b55a733aa767256f033011d75d492725c0662e6e8eed89ec9429c77ac007d31","source":{"kind":"arxiv","id":"2407.16397","version":1},"attestation_state":"computed","paper":{"title":"On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinshan Zeng, Shengkun Zhu, Sheng Wang, Xiaodong Li, Yuan Sun, Yuan Yao, Zhiyong Peng","submitted_at":"2024-07-23T11:35:42Z","abstract_excerpt":"Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL) is an approach that aims to reduce the impact of statistical heterogeneity by developing personalized models for individual users, while also inherently providing benefits in terms of fairness and robustness. However, existing PFL frameworks focus on improving the performance of personalized models while neglecting the global model. Moreover, these frameworks achieve sublinear convergence rates and rely on strong as"},"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":"2407.16397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T11:35:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"053774eaace5897fd623500b67b69087ad21d00945510996f2118a9229dceec7","abstract_canon_sha256":"bf9cbe5d6443dfac38ed36ab56a7b7aec168881917a0c8b461077521d1145fa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:32.522371Z","signature_b64":"eZ/Zfjervam19HLPO/RoMTvdOEYDV5i00oJPdO6fMHYCcQxLuDbQDHLTxdY/eDoiuEx1aBr88+XQOAVRZ6ILBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b55a733aa767256f033011d75d492725c0662e6e8eed89ec9429c77ac007d31","last_reissued_at":"2026-07-05T08:47:32.521861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:32.521861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinshan Zeng, Shengkun Zhu, Sheng Wang, Xiaodong Li, Yuan Sun, Yuan Yao, Zhiyong Peng","submitted_at":"2024-07-23T11:35:42Z","abstract_excerpt":"Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL) is an approach that aims to reduce the impact of statistical heterogeneity by developing personalized models for individual users, while also inherently providing benefits in terms of fairness and robustness. However, existing PFL frameworks focus on improving the performance of personalized models while neglecting the global model. Moreover, these frameworks achieve sublinear convergence rates and rely on strong as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16397","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/2407.16397/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":"2407.16397","created_at":"2026-07-05T08:47:32.521915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16397v1","created_at":"2026-07-05T08:47:32.521915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16397","created_at":"2026-07-05T08:47:32.521915+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNK2OM5KOZZF","created_at":"2026-07-05T08:47:32.521915+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNK2OM5KOZZFN4BT","created_at":"2026-07-05T08:47:32.521915+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNK2OM5K","created_at":"2026-07-05T08:47:32.521915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04672","citing_title":"FedAPM: Federated Learning via ADMM with Partial Model Personalization","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ","json":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ.json","graph_json":"https://pith.science/api/pith-number/FNK2OM5KOZZFN4BTAEOXLVESOJ/graph.json","events_json":"https://pith.science/api/pith-number/FNK2OM5KOZZFN4BTAEOXLVESOJ/events.json","paper":"https://pith.science/paper/FNK2OM5K"},"agent_actions":{"view_html":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ","download_json":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ.json","view_paper":"https://pith.science/paper/FNK2OM5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16397&json=true","fetch_graph":"https://pith.science/api/pith-number/FNK2OM5KOZZFN4BTAEOXLVESOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FNK2OM5KOZZFN4BTAEOXLVESOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ/action/storage_attestation","attest_author":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ/action/author_attestation","sign_citation":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ/action/citation_signature","submit_replication":"https://pith.science/pith/FNK2OM5KOZZFN4BTAEOXLVESOJ/action/replication_record"}},"created_at":"2026-07-05T08:47:32.521915+00:00","updated_at":"2026-07-05T08:47:32.521915+00:00"}