{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5UATIKYIQBY3RK4JHXWDMPNR6G","short_pith_number":"pith:5UATIKYI","schema_version":"1.0","canonical_sha256":"ed01342b088071b8ab893dec363db1f183a1d21e691f8d10ebfed0c6e4962a4e","source":{"kind":"arxiv","id":"2309.01275","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Abdellatif Kobbane, Hamza Reguieg, Mohamed El Kamili, Mohammed El Hanjri","submitted_at":"2023-09-03T21:33:15Z","abstract_excerpt":"In this paper, we investigate Federated Learning (FL), a paradigm of machine learning that allows for decentralized model training on devices without sharing raw data, there by preserving data privacy. In particular, we compare two strategies within this paradigm: Federated Averaging (FedAvg) and Personalized Federated Averaging (Per-FedAvg), focusing on their performance with Non-Identically and Independently Distributed (Non-IID) data. Our analysis shows that the level of data heterogeneity, modeled using a Dirichlet distribution, significantly affects the performance of both strategies, wit"},"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":"2309.01275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-03T21:33:15Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"3323110cfeff46268487fe034e11f593657276574d5fdc04dc75cff1d74c511e","abstract_canon_sha256":"29df17bbb8be1d13db9e9ec0e26148898e56aa4b37b434f3875de089524a5d71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:35.520650Z","signature_b64":"jSdPyModZ2Kq67U1kD5PiM+XbX0/6ihw/bsP9yxAiFRHwc7h5GT11MdwS4N4O84ESsrMtkgR/BgXLD77INieAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed01342b088071b8ab893dec363db1f183a1d21e691f8d10ebfed0c6e4962a4e","last_reissued_at":"2026-07-05T06:47:35.520215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:35.520215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Abdellatif Kobbane, Hamza Reguieg, Mohamed El Kamili, Mohammed El Hanjri","submitted_at":"2023-09-03T21:33:15Z","abstract_excerpt":"In this paper, we investigate Federated Learning (FL), a paradigm of machine learning that allows for decentralized model training on devices without sharing raw data, there by preserving data privacy. In particular, we compare two strategies within this paradigm: Federated Averaging (FedAvg) and Personalized Federated Averaging (Per-FedAvg), focusing on their performance with Non-Identically and Independently Distributed (Non-IID) data. Our analysis shows that the level of data heterogeneity, modeled using a Dirichlet distribution, significantly affects the performance of both strategies, wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01275","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/2309.01275/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":"2309.01275","created_at":"2026-07-05T06:47:35.520276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01275v1","created_at":"2026-07-05T06:47:35.520276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01275","created_at":"2026-07-05T06:47:35.520276+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UATIKYIQBY3","created_at":"2026-07-05T06:47:35.520276+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UATIKYIQBY3RK4J","created_at":"2026-07-05T06:47:35.520276+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UATIKYI","created_at":"2026-07-05T06:47:35.520276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18904","citing_title":"FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G","json":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G.json","graph_json":"https://pith.science/api/pith-number/5UATIKYIQBY3RK4JHXWDMPNR6G/graph.json","events_json":"https://pith.science/api/pith-number/5UATIKYIQBY3RK4JHXWDMPNR6G/events.json","paper":"https://pith.science/paper/5UATIKYI"},"agent_actions":{"view_html":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G","download_json":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G.json","view_paper":"https://pith.science/paper/5UATIKYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01275&json=true","fetch_graph":"https://pith.science/api/pith-number/5UATIKYIQBY3RK4JHXWDMPNR6G/graph.json","fetch_events":"https://pith.science/api/pith-number/5UATIKYIQBY3RK4JHXWDMPNR6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G/action/storage_attestation","attest_author":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G/action/author_attestation","sign_citation":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G/action/citation_signature","submit_replication":"https://pith.science/pith/5UATIKYIQBY3RK4JHXWDMPNR6G/action/replication_record"}},"created_at":"2026-07-05T06:47:35.520276+00:00","updated_at":"2026-07-05T06:47:35.520276+00:00"}