{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OBEFFBWKWS2GZBLGU6HHH45QGB","short_pith_number":"pith:OBEFFBWK","schema_version":"1.0","canonical_sha256":"70485286cab4b46c8566a78e73f3b030403358746ef04161a98a32147e04b56d","source":{"kind":"arxiv","id":"2012.04221","version":3},"attestation_state":"computed","paper":{"title":"Ditto: Fair and Robust Federated Learning Through Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmad Beirami, Shengyuan Hu, Tian Li, Virginia Smith","submitted_at":"2020-12-08T05:15:39Z","abstract_excerpt":"Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robust"},"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":"2012.04221","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T05:15:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"004f73cd697f65689c777017f60111e3af857d7f21ae585339e7baf7725122bc","abstract_canon_sha256":"c088bcbf0d73ccd5ff7a552fcb1a87bf04660ffdef165c83f68292612153fe67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:52.017635Z","signature_b64":"evRARGUxxCGOxenZEEH5ibWY7vJws1jSa+LT9BsBNypfqR4L/cLYfByXbpvzsU80joGh7qwCN3HB2QlYJsQnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70485286cab4b46c8566a78e73f3b030403358746ef04161a98a32147e04b56d","last_reissued_at":"2026-07-05T02:49:52.017131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:52.017131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ditto: Fair and Robust Federated Learning Through Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmad Beirami, Shengyuan Hu, Tian Li, Virginia Smith","submitted_at":"2020-12-08T05:15:39Z","abstract_excerpt":"Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04221","kind":"arxiv","version":3},"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/2012.04221/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":"2012.04221","created_at":"2026-07-05T02:49:52.017187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04221v3","created_at":"2026-07-05T02:49:52.017187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04221","created_at":"2026-07-05T02:49:52.017187+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBEFFBWKWS2G","created_at":"2026-07-05T02:49:52.017187+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBEFFBWKWS2GZBLG","created_at":"2026-07-05T02:49:52.017187+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBEFFBWK","created_at":"2026-07-05T02:49:52.017187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20276","citing_title":"OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB","json":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB.json","graph_json":"https://pith.science/api/pith-number/OBEFFBWKWS2GZBLGU6HHH45QGB/graph.json","events_json":"https://pith.science/api/pith-number/OBEFFBWKWS2GZBLGU6HHH45QGB/events.json","paper":"https://pith.science/paper/OBEFFBWK"},"agent_actions":{"view_html":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB","download_json":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB.json","view_paper":"https://pith.science/paper/OBEFFBWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04221&json=true","fetch_graph":"https://pith.science/api/pith-number/OBEFFBWKWS2GZBLGU6HHH45QGB/graph.json","fetch_events":"https://pith.science/api/pith-number/OBEFFBWKWS2GZBLGU6HHH45QGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB/action/storage_attestation","attest_author":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB/action/author_attestation","sign_citation":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB/action/citation_signature","submit_replication":"https://pith.science/pith/OBEFFBWKWS2GZBLGU6HHH45QGB/action/replication_record"}},"created_at":"2026-07-05T02:49:52.017187+00:00","updated_at":"2026-07-05T02:49:52.017187+00:00"}