{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:THLU36ZP72L2PFBSIGZV2YLOJD","short_pith_number":"pith:THLU36ZP","schema_version":"1.0","canonical_sha256":"99d74dfb2ffe97a7943241b35d616e48cb86152eea67739d8fd0fbfde433ac24","source":{"kind":"arxiv","id":"2108.08647","version":4},"attestation_state":"computed","paper":{"title":"Multi-Center Federated Learning: Clients Clustering for Better Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Ming Xie, Tao Shen, Tianyi Zhou, Xianzhi Wang","submitted_at":"2021-08-19T12:20:31Z","abstract_excerpt":"Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy risk of collaborative training since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of statistical heterogeneity that is commonly encountered in personalized decision-making, e.g., non-IID data over different clients. Existing FL approaches usually update a single global model t"},"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":"2108.08647","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-19T12:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"382a9d74d1548f8ece79ba525cc9a90e7b0590f37db35f3a88161a1adc48e52d","abstract_canon_sha256":"1f98191b3d10c3a9d4a08b7c49d98f96b796e8c1e0777476db09ca5062f189e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:03.626296Z","signature_b64":"Cn5UWrjhb5QtXkPKIOr6VBX5JN8Kg3j9Bc0mxDtTYNbn0pu3kgqxKbcKX6hPk31wqrfWbN5aGEF8Qe9Nf+C5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d74dfb2ffe97a7943241b35d616e48cb86152eea67739d8fd0fbfde433ac24","last_reissued_at":"2026-07-05T05:37:03.625778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:03.625778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Center Federated Learning: Clients Clustering for Better Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Ming Xie, Tao Shen, Tianyi Zhou, Xianzhi Wang","submitted_at":"2021-08-19T12:20:31Z","abstract_excerpt":"Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy risk of collaborative training since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of statistical heterogeneity that is commonly encountered in personalized decision-making, e.g., non-IID data over different clients. Existing FL approaches usually update a single global model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08647","kind":"arxiv","version":4},"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/2108.08647/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":"2108.08647","created_at":"2026-07-05T05:37:03.625837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08647v4","created_at":"2026-07-05T05:37:03.625837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08647","created_at":"2026-07-05T05:37:03.625837+00:00"},{"alias_kind":"pith_short_12","alias_value":"THLU36ZP72L2","created_at":"2026-07-05T05:37:03.625837+00:00"},{"alias_kind":"pith_short_16","alias_value":"THLU36ZP72L2PFBS","created_at":"2026-07-05T05:37:03.625837+00:00"},{"alias_kind":"pith_short_8","alias_value":"THLU36ZP","created_at":"2026-07-05T05:37:03.625837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10430","citing_title":"Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD","json":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD.json","graph_json":"https://pith.science/api/pith-number/THLU36ZP72L2PFBSIGZV2YLOJD/graph.json","events_json":"https://pith.science/api/pith-number/THLU36ZP72L2PFBSIGZV2YLOJD/events.json","paper":"https://pith.science/paper/THLU36ZP"},"agent_actions":{"view_html":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD","download_json":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD.json","view_paper":"https://pith.science/paper/THLU36ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08647&json=true","fetch_graph":"https://pith.science/api/pith-number/THLU36ZP72L2PFBSIGZV2YLOJD/graph.json","fetch_events":"https://pith.science/api/pith-number/THLU36ZP72L2PFBSIGZV2YLOJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD/action/storage_attestation","attest_author":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD/action/author_attestation","sign_citation":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD/action/citation_signature","submit_replication":"https://pith.science/pith/THLU36ZP72L2PFBSIGZV2YLOJD/action/replication_record"}},"created_at":"2026-07-05T05:37:03.625837+00:00","updated_at":"2026-07-05T05:37:03.625837+00:00"}