{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J3BDTUR7CWF32ID36UEKBJOMJ4","short_pith_number":"pith:J3BDTUR7","schema_version":"1.0","canonical_sha256":"4ec239d23f158bbd207bf508a0a5cc4f3874f9b72c485fb29c8cc46ebf80ea2a","source":{"kind":"arxiv","id":"2212.01519","version":3},"attestation_state":"computed","paper":{"title":"Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Defeng Sun, Shuai Wang, Tony Q. S. Quek, Tsung-Hui Chang, Yanqing Xu, Zhiguo Wang","submitted_at":"2022-12-03T03:27:51Z","abstract_excerpt":"As a novel distributed learning paradigm, federated learning (FL) faces serious challenges in dealing with massive clients with heterogeneous data distribution and computation and communication resources. Various client-variance-reduction schemes and client sampling strategies have been respectively introduced to improve the robustness of FL. Among others, primal-dual algorithms such as the alternating direction of method multipliers (ADMM) have been found being resilient to data distribution and outperform most of the primal-only FL algorithms. However, the reason behind remains a mystery sti"},"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":"2212.01519","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-03T03:27:51Z","cross_cats_sorted":[],"title_canon_sha256":"5f22b1349863a51c162e0b55884b902f328162563e1fd1235d207a128bc274fd","abstract_canon_sha256":"3f904604319fd313136a418354553b953e85e410f3343e11ebf786beb372aa6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:04.504155Z","signature_b64":"5bDIVAH2aFvDjZnaJoG/G61a+viMrGMiXRhfYV9jYkd9JkVbyoJyKHOEvHAm3ae3kIP0tPcZGumZyjEyMY4+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec239d23f158bbd207bf508a0a5cc4f3874f9b72c485fb29c8cc46ebf80ea2a","last_reissued_at":"2026-07-05T05:34:04.503695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:04.503695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Defeng Sun, Shuai Wang, Tony Q. S. Quek, Tsung-Hui Chang, Yanqing Xu, Zhiguo Wang","submitted_at":"2022-12-03T03:27:51Z","abstract_excerpt":"As a novel distributed learning paradigm, federated learning (FL) faces serious challenges in dealing with massive clients with heterogeneous data distribution and computation and communication resources. Various client-variance-reduction schemes and client sampling strategies have been respectively introduced to improve the robustness of FL. Among others, primal-dual algorithms such as the alternating direction of method multipliers (ADMM) have been found being resilient to data distribution and outperform most of the primal-only FL algorithms. However, the reason behind remains a mystery sti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01519","kind":"arxiv","version":3},"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/2212.01519/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":"2212.01519","created_at":"2026-07-05T05:34:04.503759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01519v3","created_at":"2026-07-05T05:34:04.503759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01519","created_at":"2026-07-05T05:34:04.503759+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3BDTUR7CWF3","created_at":"2026-07-05T05:34:04.503759+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3BDTUR7CWF32ID3","created_at":"2026-07-05T05:34:04.503759+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3BDTUR7","created_at":"2026-07-05T05:34:04.503759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02887","citing_title":"Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4","json":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4.json","graph_json":"https://pith.science/api/pith-number/J3BDTUR7CWF32ID36UEKBJOMJ4/graph.json","events_json":"https://pith.science/api/pith-number/J3BDTUR7CWF32ID36UEKBJOMJ4/events.json","paper":"https://pith.science/paper/J3BDTUR7"},"agent_actions":{"view_html":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4","download_json":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4.json","view_paper":"https://pith.science/paper/J3BDTUR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01519&json=true","fetch_graph":"https://pith.science/api/pith-number/J3BDTUR7CWF32ID36UEKBJOMJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/J3BDTUR7CWF32ID36UEKBJOMJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4/action/storage_attestation","attest_author":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4/action/author_attestation","sign_citation":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4/action/citation_signature","submit_replication":"https://pith.science/pith/J3BDTUR7CWF32ID36UEKBJOMJ4/action/replication_record"}},"created_at":"2026-07-05T05:34:04.503759+00:00","updated_at":"2026-07-05T05:34:04.503759+00:00"}