{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6IN2ZI6NLSKFSYYI5NXBOQP2AA","short_pith_number":"pith:6IN2ZI6N","schema_version":"1.0","canonical_sha256":"f21baca3cd5c94596308eb6e1741fa001d8bac1d3a02778508cd9e30ebffd77d","source":{"kind":"arxiv","id":"2206.01432","version":1},"attestation_state":"computed","paper":{"title":"On the Generalization of Wasserstein Robust Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Canh T. Dinh, Long Tan Le, Nguyen H. Tran, Tuan Dung Nguyen, Tung-Anh Nguyen","submitted_at":"2022-06-03T07:44:21Z","abstract_excerpt":"In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust optimization scheme called WAFL. Leveraging its duality, we frame WAFL as an empirical surrogate risk minimization problem, and solve it using a local SGD-based algorithm with convergence guarantees. We show that the robustness of WAFL is more general than related approaches, and the generalization bound is robust to all adversarial distributions inside the Wasserstein ball (am"},"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":"2206.01432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T07:44:21Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"697b15c30c028e310b243b8d074ac0cf5f0197adcaefe4d4dcf5db8e939bc28d","abstract_canon_sha256":"4740f3a1d26986d80d2b3103845ff068c9782f9d0f273a56e31be3e5afc92366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:47.550541Z","signature_b64":"5kMBQP25JVZbim0RgxMmQLIv6ugk9ATn2IKF2QDvaC76K6vOwn9JFvf+530nbSyQnzY7tsWBfIQziTfUUsOVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f21baca3cd5c94596308eb6e1741fa001d8bac1d3a02778508cd9e30ebffd77d","last_reissued_at":"2026-07-05T04:28:47.550034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:47.550034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization of Wasserstein Robust Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Canh T. Dinh, Long Tan Le, Nguyen H. Tran, Tuan Dung Nguyen, Tung-Anh Nguyen","submitted_at":"2022-06-03T07:44:21Z","abstract_excerpt":"In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust optimization scheme called WAFL. Leveraging its duality, we frame WAFL as an empirical surrogate risk minimization problem, and solve it using a local SGD-based algorithm with convergence guarantees. We show that the robustness of WAFL is more general than related approaches, and the generalization bound is robust to all adversarial distributions inside the Wasserstein ball (am"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01432","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/2206.01432/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":"2206.01432","created_at":"2026-07-05T04:28:47.550093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01432v1","created_at":"2026-07-05T04:28:47.550093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01432","created_at":"2026-07-05T04:28:47.550093+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IN2ZI6NLSKF","created_at":"2026-07-05T04:28:47.550093+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IN2ZI6NLSKFSYYI","created_at":"2026-07-05T04:28:47.550093+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IN2ZI6N","created_at":"2026-07-05T04:28:47.550093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10325","citing_title":"Convergence of Agnostic Federated Averaging","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA","json":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA.json","graph_json":"https://pith.science/api/pith-number/6IN2ZI6NLSKFSYYI5NXBOQP2AA/graph.json","events_json":"https://pith.science/api/pith-number/6IN2ZI6NLSKFSYYI5NXBOQP2AA/events.json","paper":"https://pith.science/paper/6IN2ZI6N"},"agent_actions":{"view_html":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA","download_json":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA.json","view_paper":"https://pith.science/paper/6IN2ZI6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01432&json=true","fetch_graph":"https://pith.science/api/pith-number/6IN2ZI6NLSKFSYYI5NXBOQP2AA/graph.json","fetch_events":"https://pith.science/api/pith-number/6IN2ZI6NLSKFSYYI5NXBOQP2AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA/action/storage_attestation","attest_author":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA/action/author_attestation","sign_citation":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA/action/citation_signature","submit_replication":"https://pith.science/pith/6IN2ZI6NLSKFSYYI5NXBOQP2AA/action/replication_record"}},"created_at":"2026-07-05T04:28:47.550093+00:00","updated_at":"2026-07-05T04:28:47.550093+00:00"}