{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KO7OSITBHJ6ERNXKESGVCFUZY5","short_pith_number":"pith:KO7OSITB","schema_version":"1.0","canonical_sha256":"53bee922613a7c48b6ea248d511699c768246e42715f253f5dd8caf2c2bb5c48","source":{"kind":"arxiv","id":"2302.04083","version":2},"attestation_state":"computed","paper":{"title":"Improving the Model Consistency of Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Dacheng Tao, Kang Wei, Li Shen, Xueqian Wang, Yan Sun, Yifan Shi","submitted_at":"2023-02-08T14:37:34Z","abstract_excerpt":"To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network. However, existing DFL suffers from high inconsistency among local clients, which results in severe distribution shift and inferior performance compared with centralized FL (CFL), especially on heterogeneous data or sparse communication topology. To alleviate this issue, we propose two DFL algorithms named DFedSAM and DFedSAM-MGS to improve the performance of DFL. S"},"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":"2302.04083","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T14:37:34Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"35d17bdcc23d03f91ff8e41fa75fa4fe73ce6c8761cb7e234d3e6ec100dfad91","abstract_canon_sha256":"56d96c5b2c109b1cbe33a3391395cd92f8eaa2a6013719fa093fdcc8c50abfd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:02.480827Z","signature_b64":"dlihJlK4PD87fwkpBCPP4FMr8F6hqysWPcWs0s3FafNf8m06qJwFtCOiUPk2gfqAwclgzZG9BEwxIaR8tkd7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53bee922613a7c48b6ea248d511699c768246e42715f253f5dd8caf2c2bb5c48","last_reissued_at":"2026-07-05T06:19:02.480327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:02.480327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Model Consistency of Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Dacheng Tao, Kang Wei, Li Shen, Xueqian Wang, Yan Sun, Yifan Shi","submitted_at":"2023-02-08T14:37:34Z","abstract_excerpt":"To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network. However, existing DFL suffers from high inconsistency among local clients, which results in severe distribution shift and inferior performance compared with centralized FL (CFL), especially on heterogeneous data or sparse communication topology. To alleviate this issue, we propose two DFL algorithms named DFedSAM and DFedSAM-MGS to improve the performance of DFL. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04083","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/2302.04083/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":"2302.04083","created_at":"2026-07-05T06:19:02.480389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04083v2","created_at":"2026-07-05T06:19:02.480389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04083","created_at":"2026-07-05T06:19:02.480389+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO7OSITBHJ6E","created_at":"2026-07-05T06:19:02.480389+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO7OSITBHJ6ERNXK","created_at":"2026-07-05T06:19:02.480389+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO7OSITB","created_at":"2026-07-05T06:19:02.480389+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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5","json":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5.json","graph_json":"https://pith.science/api/pith-number/KO7OSITBHJ6ERNXKESGVCFUZY5/graph.json","events_json":"https://pith.science/api/pith-number/KO7OSITBHJ6ERNXKESGVCFUZY5/events.json","paper":"https://pith.science/paper/KO7OSITB"},"agent_actions":{"view_html":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5","download_json":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5.json","view_paper":"https://pith.science/paper/KO7OSITB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04083&json=true","fetch_graph":"https://pith.science/api/pith-number/KO7OSITBHJ6ERNXKESGVCFUZY5/graph.json","fetch_events":"https://pith.science/api/pith-number/KO7OSITBHJ6ERNXKESGVCFUZY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5/action/storage_attestation","attest_author":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5/action/author_attestation","sign_citation":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5/action/citation_signature","submit_replication":"https://pith.science/pith/KO7OSITBHJ6ERNXKESGVCFUZY5/action/replication_record"}},"created_at":"2026-07-05T06:19:02.480389+00:00","updated_at":"2026-07-05T06:19:02.480389+00:00"}