{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SGQPJFXIGAHGDP6PCNOZUK34MW","short_pith_number":"pith:SGQPJFXI","schema_version":"1.0","canonical_sha256":"91a0f496e8300e61bfcf135d9a2b7c65ab32ede029b7eb5d59274c2ae6bec0ea","source":{"kind":"arxiv","id":"2202.06187","version":2},"attestation_state":"computed","paper":{"title":"On the Convergence of Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jie Ma, Jing Jiang, Tianyi Zhou","submitted_at":"2022-02-13T02:39:19Z","abstract_excerpt":"Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL). Most existing FL methods focus on two extremes: 1) to learn a shared model to serve all clients with non-IID data, and 2) to learn personalized models for each client, namely personalized FL. There is a trade-off solution, namely clustered FL or cluster-wise personalized FL, which aims to cluster similar clients into one cluster, and then learn a shared model for all clients within a cluster. This paper is to revisit the research of clustered FL by formulating them i"},"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":"2202.06187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T02:39:19Z","cross_cats_sorted":[],"title_canon_sha256":"b16e95354d7eab0ab39c199903685f8be85bd45ad66c54c978f46d371e19890d","abstract_canon_sha256":"aeb51fb45a2ff65ff6594973c7eaa3911a27a67adb3798aa3109571c9f1b2b93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:30.236748Z","signature_b64":"sOntVxT6X/QrjXLa4CpRp0JJcisPdjmSEYYmPzMvSyilTFyau/7F3jcaoNOzIbVKo+wiWztwONyXA9605uqaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a0f496e8300e61bfcf135d9a2b7c65ab32ede029b7eb5d59274c2ae6bec0ea","last_reissued_at":"2026-07-05T04:29:30.236279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:30.236279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jie Ma, Jing Jiang, Tianyi Zhou","submitted_at":"2022-02-13T02:39:19Z","abstract_excerpt":"Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL). Most existing FL methods focus on two extremes: 1) to learn a shared model to serve all clients with non-IID data, and 2) to learn personalized models for each client, namely personalized FL. There is a trade-off solution, namely clustered FL or cluster-wise personalized FL, which aims to cluster similar clients into one cluster, and then learn a shared model for all clients within a cluster. This paper is to revisit the research of clustered FL by formulating them i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06187","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/2202.06187/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":"2202.06187","created_at":"2026-07-05T04:29:30.236354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06187v2","created_at":"2026-07-05T04:29:30.236354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06187","created_at":"2026-07-05T04:29:30.236354+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGQPJFXIGAHG","created_at":"2026-07-05T04:29:30.236354+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGQPJFXIGAHGDP6P","created_at":"2026-07-05T04:29:30.236354+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGQPJFXI","created_at":"2026-07-05T04:29:30.236354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01587","citing_title":"One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW","json":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW.json","graph_json":"https://pith.science/api/pith-number/SGQPJFXIGAHGDP6PCNOZUK34MW/graph.json","events_json":"https://pith.science/api/pith-number/SGQPJFXIGAHGDP6PCNOZUK34MW/events.json","paper":"https://pith.science/paper/SGQPJFXI"},"agent_actions":{"view_html":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW","download_json":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW.json","view_paper":"https://pith.science/paper/SGQPJFXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06187&json=true","fetch_graph":"https://pith.science/api/pith-number/SGQPJFXIGAHGDP6PCNOZUK34MW/graph.json","fetch_events":"https://pith.science/api/pith-number/SGQPJFXIGAHGDP6PCNOZUK34MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW/action/storage_attestation","attest_author":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW/action/author_attestation","sign_citation":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW/action/citation_signature","submit_replication":"https://pith.science/pith/SGQPJFXIGAHGDP6PCNOZUK34MW/action/replication_record"}},"created_at":"2026-07-05T04:29:30.236354+00:00","updated_at":"2026-07-05T04:29:30.236354+00:00"}