{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UGIVV4FS6ZMCCLJJPDOSOZ7N2K","short_pith_number":"pith:UGIVV4FS","schema_version":"1.0","canonical_sha256":"a1915af0b2f658212d2978dd2767edd2939449f3a1cb817316e304a003d60d66","source":{"kind":"arxiv","id":"2105.05883","version":2},"attestation_state":"computed","paper":{"title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Laetitia Kameni, Marco Lorenzi, Richard Vidal, Yann Fraboni","submitted_at":"2021-05-12T18:19:20Z","abstract_excerpt":"This work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training stability. To overcome this issue, we introduce \\textit{clustered sampling} for clients selection. We prove that clustered sampling leads to better clients representatitivity and to reduced variance of the clients stochastic aggregation weights in FL. Compatibly with our theory, we provide two different clustering approaches enabling clients aggregation based"},"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":"2105.05883","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-12T18:19:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa178e9a911efff993cfd83dd5c1124089a172f967a29f7b280b9cdc5655940b","abstract_canon_sha256":"7fb4df4c7bc79c673abe48d3a4ee4cdec948e46cd484c618bf27d4117e0d7aa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:05.045462Z","signature_b64":"2QiphFpYiv7ovh7AGbSycspHBuEEOd6eICO8t1WQSBPoN6LaFsNMoTKuGM++cbgrBienqc2dFn2j2S6T613ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1915af0b2f658212d2978dd2767edd2939449f3a1cb817316e304a003d60d66","last_reissued_at":"2026-07-05T02:42:05.045050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:05.045050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Laetitia Kameni, Marco Lorenzi, Richard Vidal, Yann Fraboni","submitted_at":"2021-05-12T18:19:20Z","abstract_excerpt":"This work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training stability. To overcome this issue, we introduce \\textit{clustered sampling} for clients selection. We prove that clustered sampling leads to better clients representatitivity and to reduced variance of the clients stochastic aggregation weights in FL. Compatibly with our theory, we provide two different clustering approaches enabling clients aggregation based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05883","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/2105.05883/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":"2105.05883","created_at":"2026-07-05T02:42:05.045107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05883v2","created_at":"2026-07-05T02:42:05.045107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05883","created_at":"2026-07-05T02:42:05.045107+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGIVV4FS6ZMC","created_at":"2026-07-05T02:42:05.045107+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGIVV4FS6ZMCCLJJ","created_at":"2026-07-05T02:42:05.045107+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGIVV4FS","created_at":"2026-07-05T02:42:05.045107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14226","citing_title":"FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K","json":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K.json","graph_json":"https://pith.science/api/pith-number/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/graph.json","events_json":"https://pith.science/api/pith-number/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/events.json","paper":"https://pith.science/paper/UGIVV4FS"},"agent_actions":{"view_html":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K","download_json":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K.json","view_paper":"https://pith.science/paper/UGIVV4FS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05883&json=true","fetch_graph":"https://pith.science/api/pith-number/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/graph.json","fetch_events":"https://pith.science/api/pith-number/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/action/storage_attestation","attest_author":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/action/author_attestation","sign_citation":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/action/citation_signature","submit_replication":"https://pith.science/pith/UGIVV4FS6ZMCCLJJPDOSOZ7N2K/action/replication_record"}},"created_at":"2026-07-05T02:42:05.045107+00:00","updated_at":"2026-07-05T02:42:05.045107+00:00"}