{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZTD5PHVWLUAKI2PDJ76S7HH5RG","short_pith_number":"pith:ZTD5PHVW","schema_version":"1.0","canonical_sha256":"ccc7d79eb65d00a469e34ffd2f9cfd89903fdc636ea3e901289b9647a5056951","source":{"kind":"arxiv","id":"2302.05726","version":1},"attestation_state":"computed","paper":{"title":"Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Bo Liu, Dacheng Tao, Li Shen, Yan Sun, Yixing Liu, Zhengtao Ding","submitted_at":"2023-02-11T15:46:28Z","abstract_excerpt":"Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset. To address these issues, we propose a novel federated learning algorithm, named FedMIM, which adopts the multi-step inertial momentum on the edge devices and enhances t"},"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":"2302.05726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-02-11T15:46:28Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"3ebd7dd6be2057857f4078b66cc51747d97878b52410b3e1d0ee3db19c1c3782","abstract_canon_sha256":"438803ed9171f1c895c0bbeb8dc261913d32b80d02cd864c86e6c4a3217c5d1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:57.522764Z","signature_b64":"N/eqDZw3/BUqs9VVQr5LEI7lQuDCObtwMTW6iMtaB+kWSGtcAv/8LEOC1Prp+TE2cpKLp5tGUfg+dMe4SaDABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccc7d79eb65d00a469e34ffd2f9cfd89903fdc636ea3e901289b9647a5056951","last_reissued_at":"2026-07-05T05:40:57.522094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:57.522094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Bo Liu, Dacheng Tao, Li Shen, Yan Sun, Yixing Liu, Zhengtao Ding","submitted_at":"2023-02-11T15:46:28Z","abstract_excerpt":"Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset. To address these issues, we propose a novel federated learning algorithm, named FedMIM, which adopts the multi-step inertial momentum on the edge devices and enhances t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05726","kind":"arxiv","version":1},"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/2302.05726/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":"2302.05726","created_at":"2026-07-05T05:40:57.522188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05726v1","created_at":"2026-07-05T05:40:57.522188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05726","created_at":"2026-07-05T05:40:57.522188+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTD5PHVWLUAK","created_at":"2026-07-05T05:40:57.522188+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTD5PHVWLUAKI2PD","created_at":"2026-07-05T05:40:57.522188+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTD5PHVW","created_at":"2026-07-05T05:40:57.522188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12768","citing_title":"Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG","json":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG.json","graph_json":"https://pith.science/api/pith-number/ZTD5PHVWLUAKI2PDJ76S7HH5RG/graph.json","events_json":"https://pith.science/api/pith-number/ZTD5PHVWLUAKI2PDJ76S7HH5RG/events.json","paper":"https://pith.science/paper/ZTD5PHVW"},"agent_actions":{"view_html":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG","download_json":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG.json","view_paper":"https://pith.science/paper/ZTD5PHVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05726&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTD5PHVWLUAKI2PDJ76S7HH5RG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTD5PHVWLUAKI2PDJ76S7HH5RG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG/action/storage_attestation","attest_author":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG/action/author_attestation","sign_citation":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG/action/citation_signature","submit_replication":"https://pith.science/pith/ZTD5PHVWLUAKI2PDJ76S7HH5RG/action/replication_record"}},"created_at":"2026-07-05T05:40:57.522188+00:00","updated_at":"2026-07-05T05:40:57.522188+00:00"}