{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:K5ZERAGTIRRSALXVVAVZ6GX35E","short_pith_number":"pith:K5ZERAGT","schema_version":"1.0","canonical_sha256":"57724880d34463202ef5a82b9f1afbe9197c07d2411baf912b69b428f8646f69","source":{"kind":"arxiv","id":"2106.13039","version":2},"attestation_state":"computed","paper":{"title":"Low-Latency Federated Learning over Wireless Channels with Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Cailian Chen, Chuan Ma, H. Vincent Poor, Jun Li, Kang Wei, Ming Ding, Shi Jin, Zhu Han","submitted_at":"2021-06-20T13:51:18Z","abstract_excerpt":"In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. The performance of uploaded models in such situations can vary widely due to imbalanced data distributions, potential demands on privacy protections, and quality of transmissions. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement. We solve this problem in the framework of multi-agent multi-armed bandit (MAMAB) to deal with the situation wher"},"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":"2106.13039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-06-20T13:51:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af90a85486db56e67f89573168dfe074c5745d14414bf0da1bbf9e72b602d415","abstract_canon_sha256":"4de22c1c64904649769d01b88fe2e8bed9f6bac9ac685a3264f028490f540ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:30.203479Z","signature_b64":"rA4hoQvHrabgeBl3h312rHtDxOiJmh437wfO+wk4hM6lZPgTP4pEqdk2t7tKsk15M1NbzQnMPsBR6o3gNln3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57724880d34463202ef5a82b9f1afbe9197c07d2411baf912b69b428f8646f69","last_reissued_at":"2026-07-05T03:13:30.203086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:30.203086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Latency Federated Learning over Wireless Channels with Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Cailian Chen, Chuan Ma, H. Vincent Poor, Jun Li, Kang Wei, Ming Ding, Shi Jin, Zhu Han","submitted_at":"2021-06-20T13:51:18Z","abstract_excerpt":"In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. The performance of uploaded models in such situations can vary widely due to imbalanced data distributions, potential demands on privacy protections, and quality of transmissions. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement. We solve this problem in the framework of multi-agent multi-armed bandit (MAMAB) to deal with the situation wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13039","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/2106.13039/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":"2106.13039","created_at":"2026-07-05T03:13:30.203143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13039v2","created_at":"2026-07-05T03:13:30.203143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13039","created_at":"2026-07-05T03:13:30.203143+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5ZERAGTIRRS","created_at":"2026-07-05T03:13:30.203143+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5ZERAGTIRRSALXV","created_at":"2026-07-05T03:13:30.203143+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5ZERAGT","created_at":"2026-07-05T03:13:30.203143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E","json":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E.json","graph_json":"https://pith.science/api/pith-number/K5ZERAGTIRRSALXVVAVZ6GX35E/graph.json","events_json":"https://pith.science/api/pith-number/K5ZERAGTIRRSALXVVAVZ6GX35E/events.json","paper":"https://pith.science/paper/K5ZERAGT"},"agent_actions":{"view_html":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E","download_json":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E.json","view_paper":"https://pith.science/paper/K5ZERAGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13039&json=true","fetch_graph":"https://pith.science/api/pith-number/K5ZERAGTIRRSALXVVAVZ6GX35E/graph.json","fetch_events":"https://pith.science/api/pith-number/K5ZERAGTIRRSALXVVAVZ6GX35E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E/action/storage_attestation","attest_author":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E/action/author_attestation","sign_citation":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E/action/citation_signature","submit_replication":"https://pith.science/pith/K5ZERAGTIRRSALXVVAVZ6GX35E/action/replication_record"}},"created_at":"2026-07-05T03:13:30.203143+00:00","updated_at":"2026-07-05T03:13:30.203143+00:00"}