{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AGKWHPKQARCP2TRXBAJ7QGBONM","short_pith_number":"pith:AGKWHPKQ","schema_version":"1.0","canonical_sha256":"019563bd500444fd4e370813f8182e6b20c5f91b10a8ee6371b7920fe77a1f4b","source":{"kind":"arxiv","id":"2009.06557","version":2},"attestation_state":"computed","paper":{"title":"Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guannan Liang, Jinbo Bi, Qianqian Tong","submitted_at":"2020-09-14T16:37:44Z","abstract_excerpt":"Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing. The analysis with partial device participation under non-IID and unbalanced data reflects more reality. In this work, we propose federated learning versions of adaptive gradient methods - Federated AGMs - which employ both the first-order and second-order momenta, to alleviate generalization performance deterioration caused by dissimilarity of data population among devices. To further improve the test performance, we compare several schemes of calibration for the adaptive lea"},"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":"2009.06557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T16:37:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14909c9bab24dc35425f08da35a6240224f978b66f981a6e1c38a27e6b8903e3","abstract_canon_sha256":"e62346a78654b0861744e94cf65f3a8d66784d30bd9e0bc503fb0e2c0329cf00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:14.590857Z","signature_b64":"zZkdrmYOARZGEl3C6t3XTFoNGaU2uMZ2Pq53XL2QqxHBK5tjGM+dAp3LboT59Dzkf5hOhAxUx541KtfIqH2ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"019563bd500444fd4e370813f8182e6b20c5f91b10a8ee6371b7920fe77a1f4b","last_reissued_at":"2026-07-05T02:01:14.590370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:14.590370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guannan Liang, Jinbo Bi, Qianqian Tong","submitted_at":"2020-09-14T16:37:44Z","abstract_excerpt":"Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing. The analysis with partial device participation under non-IID and unbalanced data reflects more reality. In this work, we propose federated learning versions of adaptive gradient methods - Federated AGMs - which employ both the first-order and second-order momenta, to alleviate generalization performance deterioration caused by dissimilarity of data population among devices. To further improve the test performance, we compare several schemes of calibration for the adaptive lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06557","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/2009.06557/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":"2009.06557","created_at":"2026-07-05T02:01:14.590428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.06557v2","created_at":"2026-07-05T02:01:14.590428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06557","created_at":"2026-07-05T02:01:14.590428+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGKWHPKQARCP","created_at":"2026-07-05T02:01:14.590428+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGKWHPKQARCP2TRX","created_at":"2026-07-05T02:01:14.590428+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGKWHPKQ","created_at":"2026-07-05T02:01:14.590428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03867","citing_title":"GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM","json":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM.json","graph_json":"https://pith.science/api/pith-number/AGKWHPKQARCP2TRXBAJ7QGBONM/graph.json","events_json":"https://pith.science/api/pith-number/AGKWHPKQARCP2TRXBAJ7QGBONM/events.json","paper":"https://pith.science/paper/AGKWHPKQ"},"agent_actions":{"view_html":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM","download_json":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM.json","view_paper":"https://pith.science/paper/AGKWHPKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.06557&json=true","fetch_graph":"https://pith.science/api/pith-number/AGKWHPKQARCP2TRXBAJ7QGBONM/graph.json","fetch_events":"https://pith.science/api/pith-number/AGKWHPKQARCP2TRXBAJ7QGBONM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM/action/storage_attestation","attest_author":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM/action/author_attestation","sign_citation":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM/action/citation_signature","submit_replication":"https://pith.science/pith/AGKWHPKQARCP2TRXBAJ7QGBONM/action/replication_record"}},"created_at":"2026-07-05T02:01:14.590428+00:00","updated_at":"2026-07-05T02:01:14.590428+00:00"}