{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UV3CY7RCEMBMPZATSEHFIZW7OU","short_pith_number":"pith:UV3CY7RC","schema_version":"1.0","canonical_sha256":"a5762c7e222302c7e413910e5466df7507b6a2864efb91dee9c089fcd69e1cd5","source":{"kind":"arxiv","id":"2108.08768","version":1},"attestation_state":"computed","paper":{"title":"Client Selection Approach in Support of Clustered Federated Learning over Wireless Edge Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Abdullatif Albaseer, Aiman Erbad, Ala Al-Fuqaha, Mohamed Abdallah","submitted_at":"2021-08-16T21:38:22Z","abstract_excerpt":"Clustered Federated Multitask Learning (CFL) was introduced as an efficient scheme to obtain reliable specialized models when data is imbalanced and distributed in a non-i.i.d. (non-independent and identically distributed) fashion amongst clients. While a similarity measure metric, like the cosine similarity, can be used to endow groups of the client with a specialized model, this process can be arduous as the server should involve all clients in each of the federated learning rounds. Therefore, it is imperative that a subset of clients is selected periodically due to the limited bandwidth and"},"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":"2108.08768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-08-16T21:38:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e92ea8d3f34fadbad3c87c0c20230d15ae404f89bb4016cd4e35c9e626192a9a","abstract_canon_sha256":"f7a572e22d4ebf520e32d579828819f6bde24883fda82a8440d10a5213f5509d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:13.304610Z","signature_b64":"jnBDWQ4r4mcT9JuONLBFnyWzi75+3GeAWTXXVUsfq/XA7E8QrybXzaqsm3j7XCg4hVMCDlR2GjDTeGCNwCfkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5762c7e222302c7e413910e5466df7507b6a2864efb91dee9c089fcd69e1cd5","last_reissued_at":"2026-07-05T03:07:13.304127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:13.304127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Client Selection Approach in Support of Clustered Federated Learning over Wireless Edge Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Abdullatif Albaseer, Aiman Erbad, Ala Al-Fuqaha, Mohamed Abdallah","submitted_at":"2021-08-16T21:38:22Z","abstract_excerpt":"Clustered Federated Multitask Learning (CFL) was introduced as an efficient scheme to obtain reliable specialized models when data is imbalanced and distributed in a non-i.i.d. (non-independent and identically distributed) fashion amongst clients. While a similarity measure metric, like the cosine similarity, can be used to endow groups of the client with a specialized model, this process can be arduous as the server should involve all clients in each of the federated learning rounds. Therefore, it is imperative that a subset of clients is selected periodically due to the limited bandwidth and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08768","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/2108.08768/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":"2108.08768","created_at":"2026-07-05T03:07:13.304178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08768v1","created_at":"2026-07-05T03:07:13.304178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08768","created_at":"2026-07-05T03:07:13.304178+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV3CY7RCEMBM","created_at":"2026-07-05T03:07:13.304178+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV3CY7RCEMBMPZAT","created_at":"2026-07-05T03:07:13.304178+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV3CY7RC","created_at":"2026-07-05T03:07:13.304178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10849","citing_title":"Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU","json":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU.json","graph_json":"https://pith.science/api/pith-number/UV3CY7RCEMBMPZATSEHFIZW7OU/graph.json","events_json":"https://pith.science/api/pith-number/UV3CY7RCEMBMPZATSEHFIZW7OU/events.json","paper":"https://pith.science/paper/UV3CY7RC"},"agent_actions":{"view_html":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU","download_json":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU.json","view_paper":"https://pith.science/paper/UV3CY7RC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08768&json=true","fetch_graph":"https://pith.science/api/pith-number/UV3CY7RCEMBMPZATSEHFIZW7OU/graph.json","fetch_events":"https://pith.science/api/pith-number/UV3CY7RCEMBMPZATSEHFIZW7OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU/action/storage_attestation","attest_author":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU/action/author_attestation","sign_citation":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU/action/citation_signature","submit_replication":"https://pith.science/pith/UV3CY7RCEMBMPZATSEHFIZW7OU/action/replication_record"}},"created_at":"2026-07-05T03:07:13.304178+00:00","updated_at":"2026-07-05T03:07:13.304178+00:00"}