{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HYNNLBWNCHBEEJR5ZE6UHXUSJO","short_pith_number":"pith:HYNNLBWN","schema_version":"1.0","canonical_sha256":"3e1ad586cd11c242263dc93d43de924bb33b948da441e0e794d9830eee50f318","source":{"kind":"arxiv","id":"2505.15371","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust Federated Learning with Client Drift Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaouki Ben Issaid, Mehdi Bennis, Mounssif Krouka","submitted_at":"2025-05-21T11:05:56Z","abstract_excerpt":"Federated learning (FL) faces critical challenges, particularly in heterogeneous environments where non-independent and identically distributed data across clients can lead to unfair and inefficient model performance. In this work, we introduce \\textit{DRDM}, a novel algorithm that addresses these issues by combining a distributionally robust optimization (DRO) framework with dynamic regularization to mitigate client drift. \\textit{DRDM} frames the training as a min-max optimization problem aimed at maximizing performance for the worst-case client, thereby promoting robustness and fairness. Th"},"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":"2505.15371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T11:05:56Z","cross_cats_sorted":[],"title_canon_sha256":"8ca461a9919832f0a7184279953f88f32b654cf2297872a9c0ced9a3fc53714c","abstract_canon_sha256":"9594c44a620179a2e459a0449dd497c59b0bb35c31c5050c8649c46975e9e9c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:44.330328Z","signature_b64":"WZsFL3RrtyQEn9IGM5F2I8Qj72EZmfwCvDMnHHXfNJOXtjNgl/4pt6mcy5e6GZ3c+tHsBoe2N/Dkru9MHhjrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e1ad586cd11c242263dc93d43de924bb33b948da441e0e794d9830eee50f318","last_reissued_at":"2026-07-05T11:06:44.329859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:44.329859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Federated Learning with Client Drift Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaouki Ben Issaid, Mehdi Bennis, Mounssif Krouka","submitted_at":"2025-05-21T11:05:56Z","abstract_excerpt":"Federated learning (FL) faces critical challenges, particularly in heterogeneous environments where non-independent and identically distributed data across clients can lead to unfair and inefficient model performance. In this work, we introduce \\textit{DRDM}, a novel algorithm that addresses these issues by combining a distributionally robust optimization (DRO) framework with dynamic regularization to mitigate client drift. \\textit{DRDM} frames the training as a min-max optimization problem aimed at maximizing performance for the worst-case client, thereby promoting robustness and fairness. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15371","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/2505.15371/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":"2505.15371","created_at":"2026-07-05T11:06:44.329917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15371v1","created_at":"2026-07-05T11:06:44.329917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15371","created_at":"2026-07-05T11:06:44.329917+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYNNLBWNCHBE","created_at":"2026-07-05T11:06:44.329917+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYNNLBWNCHBEEJR5","created_at":"2026-07-05T11:06:44.329917+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYNNLBWN","created_at":"2026-07-05T11:06:44.329917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO","json":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO.json","graph_json":"https://pith.science/api/pith-number/HYNNLBWNCHBEEJR5ZE6UHXUSJO/graph.json","events_json":"https://pith.science/api/pith-number/HYNNLBWNCHBEEJR5ZE6UHXUSJO/events.json","paper":"https://pith.science/paper/HYNNLBWN"},"agent_actions":{"view_html":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO","download_json":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO.json","view_paper":"https://pith.science/paper/HYNNLBWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15371&json=true","fetch_graph":"https://pith.science/api/pith-number/HYNNLBWNCHBEEJR5ZE6UHXUSJO/graph.json","fetch_events":"https://pith.science/api/pith-number/HYNNLBWNCHBEEJR5ZE6UHXUSJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO/action/storage_attestation","attest_author":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO/action/author_attestation","sign_citation":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO/action/citation_signature","submit_replication":"https://pith.science/pith/HYNNLBWNCHBEEJR5ZE6UHXUSJO/action/replication_record"}},"created_at":"2026-07-05T11:06:44.329917+00:00","updated_at":"2026-07-05T11:06:44.329917+00:00"}