{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KHDR7OJV4BTQKHHOJHB4GAIY32","short_pith_number":"pith:KHDR7OJV","schema_version":"1.0","canonical_sha256":"51c71fb935e067051cee49c3c30118de87004f878d520acfba203a40edf37ced","source":{"kind":"arxiv","id":"2403.04144","version":1},"attestation_state":"computed","paper":{"title":"FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Fei Xu, Li Chen, Md Sirajul Islam, Nian-Feng Tzeng, Simin Javaherian, Xu Yuan","submitted_at":"2024-03-07T01:50:36Z","abstract_excerpt":"Federated learning (FL) is an emerging distributed machine learning paradigm enabling collaborative model training on decentralized devices without exposing their local data. A key challenge in FL is the uneven data distribution across client devices, violating the well-known assumption of independent-and-identically-distributed (IID) training samples in conventional machine learning. Clustered federated learning (CFL) addresses this challenge by grouping clients based on the similarity of their data distributions. However, existing CFL approaches require a large number of communication rounds"},"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":"2403.04144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-03-07T01:50:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb9ddb0aaf575637983b7de428c7e0e9868c5526dd2e36bd9f6e186a12410587","abstract_canon_sha256":"6df8783b3d1b0b618fef19f22b5f3ac1506bae4d85e174e8d4561f6d84bfef75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:19.242939Z","signature_b64":"I5LIctgNt3nZ0nVmG7/KH+lCOrlUYnmXoDc3mk1aY9d7kQLm3wx/6m9wr1RXTaEeA7FH+EJwQwlWt+JkRaFxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51c71fb935e067051cee49c3c30118de87004f878d520acfba203a40edf37ced","last_reissued_at":"2026-07-05T07:53:19.242494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:19.242494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Fei Xu, Li Chen, Md Sirajul Islam, Nian-Feng Tzeng, Simin Javaherian, Xu Yuan","submitted_at":"2024-03-07T01:50:36Z","abstract_excerpt":"Federated learning (FL) is an emerging distributed machine learning paradigm enabling collaborative model training on decentralized devices without exposing their local data. A key challenge in FL is the uneven data distribution across client devices, violating the well-known assumption of independent-and-identically-distributed (IID) training samples in conventional machine learning. Clustered federated learning (CFL) addresses this challenge by grouping clients based on the similarity of their data distributions. However, existing CFL approaches require a large number of communication rounds"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04144","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/2403.04144/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":"2403.04144","created_at":"2026-07-05T07:53:19.242558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04144v1","created_at":"2026-07-05T07:53:19.242558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04144","created_at":"2026-07-05T07:53:19.242558+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHDR7OJV4BTQ","created_at":"2026-07-05T07:53:19.242558+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHDR7OJV4BTQKHHO","created_at":"2026-07-05T07:53:19.242558+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHDR7OJV","created_at":"2026-07-05T07:53:19.242558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07769","citing_title":"Clustered Federated Learning via Embedding Distributions","ref_index":1985,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32","json":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32.json","graph_json":"https://pith.science/api/pith-number/KHDR7OJV4BTQKHHOJHB4GAIY32/graph.json","events_json":"https://pith.science/api/pith-number/KHDR7OJV4BTQKHHOJHB4GAIY32/events.json","paper":"https://pith.science/paper/KHDR7OJV"},"agent_actions":{"view_html":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32","download_json":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32.json","view_paper":"https://pith.science/paper/KHDR7OJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04144&json=true","fetch_graph":"https://pith.science/api/pith-number/KHDR7OJV4BTQKHHOJHB4GAIY32/graph.json","fetch_events":"https://pith.science/api/pith-number/KHDR7OJV4BTQKHHOJHB4GAIY32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32/action/storage_attestation","attest_author":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32/action/author_attestation","sign_citation":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32/action/citation_signature","submit_replication":"https://pith.science/pith/KHDR7OJV4BTQKHHOJHB4GAIY32/action/replication_record"}},"created_at":"2026-07-05T07:53:19.242558+00:00","updated_at":"2026-07-05T07:53:19.242558+00:00"}