{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GM2MY5LT6V4UEHAWHFLSDVTB4Q","short_pith_number":"pith:GM2MY5LT","schema_version":"1.0","canonical_sha256":"3334cc7573f579421c16395721d661e430276b249e2993f3ff860085a81ef96f","source":{"kind":"arxiv","id":"2207.08391","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning for Non-IID Data via Client Variance Reduction and Adaptive Server Update","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Harikrishna Warrier, Hiep Nguyen, Lam Phan, Yogesh Gupta","submitted_at":"2022-07-18T05:58:19Z","abstract_excerpt":"Federated learning (FL) is an emerging technique used to collaboratively train a global machine learning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementation is the Non-Independent and Identical (Non-IID) data distribution across users, which slows convergence and degrades performance. To tackle this fundamental issue, we propose a method (ComFed) that enhances the whole training process on both the client and server sides. The key idea of ComFed is to simultaneously utilize client-variance reduction techniques to facilitate server aggr"},"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":"2207.08391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-18T05:58:19Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"16e46dc47e257522e55f20d4c3c22f21cd3b861c32776fe1746d99df3e626888","abstract_canon_sha256":"991138236d16950b151b6192607c5b18896cbb6d2e2ba8a9353086af7144bb2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:31.960225Z","signature_b64":"dqYp3QSS8YKssnw+bn9k2iorEGkv2huTQRHsxexUhwbdjsmDEFIk/O4HLYGlBLweMbdppF4z6oTiDueyuBR0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3334cc7573f579421c16395721d661e430276b249e2993f3ff860085a81ef96f","last_reissued_at":"2026-07-05T04:44:31.959770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:31.959770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning for Non-IID Data via Client Variance Reduction and Adaptive Server Update","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Harikrishna Warrier, Hiep Nguyen, Lam Phan, Yogesh Gupta","submitted_at":"2022-07-18T05:58:19Z","abstract_excerpt":"Federated learning (FL) is an emerging technique used to collaboratively train a global machine learning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementation is the Non-Independent and Identical (Non-IID) data distribution across users, which slows convergence and degrades performance. To tackle this fundamental issue, we propose a method (ComFed) that enhances the whole training process on both the client and server sides. The key idea of ComFed is to simultaneously utilize client-variance reduction techniques to facilitate server aggr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08391","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/2207.08391/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":"2207.08391","created_at":"2026-07-05T04:44:31.959827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08391v2","created_at":"2026-07-05T04:44:31.959827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08391","created_at":"2026-07-05T04:44:31.959827+00:00"},{"alias_kind":"pith_short_12","alias_value":"GM2MY5LT6V4U","created_at":"2026-07-05T04:44:31.959827+00:00"},{"alias_kind":"pith_short_16","alias_value":"GM2MY5LT6V4UEHAW","created_at":"2026-07-05T04:44:31.959827+00:00"},{"alias_kind":"pith_short_8","alias_value":"GM2MY5LT","created_at":"2026-07-05T04:44:31.959827+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":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q","json":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q.json","graph_json":"https://pith.science/api/pith-number/GM2MY5LT6V4UEHAWHFLSDVTB4Q/graph.json","events_json":"https://pith.science/api/pith-number/GM2MY5LT6V4UEHAWHFLSDVTB4Q/events.json","paper":"https://pith.science/paper/GM2MY5LT"},"agent_actions":{"view_html":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q","download_json":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q.json","view_paper":"https://pith.science/paper/GM2MY5LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08391&json=true","fetch_graph":"https://pith.science/api/pith-number/GM2MY5LT6V4UEHAWHFLSDVTB4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/GM2MY5LT6V4UEHAWHFLSDVTB4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q/action/storage_attestation","attest_author":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q/action/author_attestation","sign_citation":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q/action/citation_signature","submit_replication":"https://pith.science/pith/GM2MY5LT6V4UEHAWHFLSDVTB4Q/action/replication_record"}},"created_at":"2026-07-05T04:44:31.959827+00:00","updated_at":"2026-07-05T04:44:31.959827+00:00"}