{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KSUTLPRV6M24KWYGDEP2P3QPO6","short_pith_number":"pith:KSUTLPRV","schema_version":"1.0","canonical_sha256":"54a935be35f335c55b06191fa7ee0f77819ec55554dac77127e2493371267222","source":{"kind":"arxiv","id":"2007.15197","version":2},"attestation_state":"computed","paper":{"title":"Communication-Efficient Federated Learning via Optimal Client Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haris Vikalo, Monica Ribero","submitted_at":"2020-07-30T02:58:00Z","abstract_excerpt":"Federated learning (FL) ameliorates privacy concerns in settings where a central server coordinates learning from data distributed across many clients. The clients train locally and communicate the models they learn to the server; aggregation of local models requires frequent communication of large amounts of information between the clients and the central server. We propose a novel, simple and efficient way of updating the central model in communication-constrained settings based on collecting models from clients with informative updates and estimating local updates that were not communicated"},"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":"2007.15197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T02:58:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b6e34337a112f8b7a19dc9e21796c89a7dbf263fbaa2b83a317326c1f9176e96","abstract_canon_sha256":"9ea6a0254e2774239631d681b4d6084301f2a2b230ec66e98af307fcd87d3c90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:05.655286Z","signature_b64":"jH/RBR+dqtQukyolMkBGJJoVBfs19H2jfvzyqrpHySWAcQm4GMLqb0E556BDkrhhjVwDZmjM7inGsL0kWh3KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a935be35f335c55b06191fa7ee0f77819ec55554dac77127e2493371267222","last_reissued_at":"2026-07-05T01:43:05.654802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:05.654802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Federated Learning via Optimal Client Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haris Vikalo, Monica Ribero","submitted_at":"2020-07-30T02:58:00Z","abstract_excerpt":"Federated learning (FL) ameliorates privacy concerns in settings where a central server coordinates learning from data distributed across many clients. The clients train locally and communicate the models they learn to the server; aggregation of local models requires frequent communication of large amounts of information between the clients and the central server. We propose a novel, simple and efficient way of updating the central model in communication-constrained settings based on collecting models from clients with informative updates and estimating local updates that were not communicated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15197","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/2007.15197/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":"2007.15197","created_at":"2026-07-05T01:43:05.654866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15197v2","created_at":"2026-07-05T01:43:05.654866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15197","created_at":"2026-07-05T01:43:05.654866+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSUTLPRV6M24","created_at":"2026-07-05T01:43:05.654866+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSUTLPRV6M24KWYG","created_at":"2026-07-05T01:43:05.654866+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSUTLPRV","created_at":"2026-07-05T01:43:05.654866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10124","citing_title":"FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20975","citing_title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20975","citing_title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6","json":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6.json","graph_json":"https://pith.science/api/pith-number/KSUTLPRV6M24KWYGDEP2P3QPO6/graph.json","events_json":"https://pith.science/api/pith-number/KSUTLPRV6M24KWYGDEP2P3QPO6/events.json","paper":"https://pith.science/paper/KSUTLPRV"},"agent_actions":{"view_html":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6","download_json":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6.json","view_paper":"https://pith.science/paper/KSUTLPRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15197&json=true","fetch_graph":"https://pith.science/api/pith-number/KSUTLPRV6M24KWYGDEP2P3QPO6/graph.json","fetch_events":"https://pith.science/api/pith-number/KSUTLPRV6M24KWYGDEP2P3QPO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6/action/storage_attestation","attest_author":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6/action/author_attestation","sign_citation":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6/action/citation_signature","submit_replication":"https://pith.science/pith/KSUTLPRV6M24KWYGDEP2P3QPO6/action/replication_record"}},"created_at":"2026-07-05T01:43:05.654866+00:00","updated_at":"2026-07-05T01:43:05.654866+00:00"}