{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MHKCUE4K6G4AFU22IB5Q5QYLPE","short_pith_number":"pith:MHKCUE4K","schema_version":"1.0","canonical_sha256":"61d42a138af1b802d35a407b0ec30b7917d64dbc13f08a84d6339ed5b92c7758","source":{"kind":"arxiv","id":"2204.03529","version":2},"attestation_state":"computed","paper":{"title":"FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nikolaos M. Freris, Yichuan Li, Yonghai Gong","submitted_at":"2022-04-07T15:58:33Z","abstract_excerpt":"Federated Learning (FL) is an emerging framework for distributed processing of large data volumes by edge devices subject to limited communication bandwidths, heterogeneity in data distributions and computational resources, as well as privacy considerations. In this paper, we introduce a new FL protocol termed FedADMM based on primal-dual optimization. The proposed method leverages dual variables to tackle statistical heterogeneity, and accommodates system heterogeneity by tolerating variable amount of work performed by clients. FedADMM maintains identical communication costs per round as FedA"},"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":"2204.03529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-07T15:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"2e06eeb4180887baae248adf2d668b510a71073bd5de4e5e852e1d46fbae5478","abstract_canon_sha256":"403161ca8d863d48722e6daaffcacf26ac08c3159628071cc19ca1a345002c62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:40.591690Z","signature_b64":"JMPdpq7UmW83k74G6NpsIGG/P4JeCJpszuOCIjl6GvuKdJwC4gQozHsldHj1tNtFnpATpBs8Kmh+5KSwFZdvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d42a138af1b802d35a407b0ec30b7917d64dbc13f08a84d6339ed5b92c7758","last_reissued_at":"2026-07-05T04:12:40.591262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:40.591262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nikolaos M. Freris, Yichuan Li, Yonghai Gong","submitted_at":"2022-04-07T15:58:33Z","abstract_excerpt":"Federated Learning (FL) is an emerging framework for distributed processing of large data volumes by edge devices subject to limited communication bandwidths, heterogeneity in data distributions and computational resources, as well as privacy considerations. In this paper, we introduce a new FL protocol termed FedADMM based on primal-dual optimization. The proposed method leverages dual variables to tackle statistical heterogeneity, and accommodates system heterogeneity by tolerating variable amount of work performed by clients. FedADMM maintains identical communication costs per round as FedA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03529","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/2204.03529/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":"2204.03529","created_at":"2026-07-05T04:12:40.591324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03529v2","created_at":"2026-07-05T04:12:40.591324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03529","created_at":"2026-07-05T04:12:40.591324+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHKCUE4K6G4A","created_at":"2026-07-05T04:12:40.591324+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHKCUE4K6G4AFU22","created_at":"2026-07-05T04:12:40.591324+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHKCUE4K","created_at":"2026-07-05T04:12:40.591324+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/MHKCUE4K6G4AFU22IB5Q5QYLPE","json":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE.json","graph_json":"https://pith.science/api/pith-number/MHKCUE4K6G4AFU22IB5Q5QYLPE/graph.json","events_json":"https://pith.science/api/pith-number/MHKCUE4K6G4AFU22IB5Q5QYLPE/events.json","paper":"https://pith.science/paper/MHKCUE4K"},"agent_actions":{"view_html":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE","download_json":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE.json","view_paper":"https://pith.science/paper/MHKCUE4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03529&json=true","fetch_graph":"https://pith.science/api/pith-number/MHKCUE4K6G4AFU22IB5Q5QYLPE/graph.json","fetch_events":"https://pith.science/api/pith-number/MHKCUE4K6G4AFU22IB5Q5QYLPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE/action/storage_attestation","attest_author":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE/action/author_attestation","sign_citation":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE/action/citation_signature","submit_replication":"https://pith.science/pith/MHKCUE4K6G4AFU22IB5Q5QYLPE/action/replication_record"}},"created_at":"2026-07-05T04:12:40.591324+00:00","updated_at":"2026-07-05T04:12:40.591324+00:00"}