{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IXB6OLK5JFETD7HBRHSHOY6U6Q","short_pith_number":"pith:IXB6OLK5","schema_version":"1.0","canonical_sha256":"45c3e72d5d494931fce189e47763d4f41db2421677d27b4261f9c27d283a7470","source":{"kind":"arxiv","id":"2012.02447","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Bias in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annie Abay, Ebube Chuba, Heiko Ludwig, Nathalie Baracaldo, Shashank Rajamoni, Yi Zhou","submitted_at":"2020-12-04T08:04:12Z","abstract_excerpt":"As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train a global model without sharing their training data. In this paper, we discuss causes of bias in FL and propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy, a key FL requirement. As data heterogeneity among parties is one of the challenging characteristics of FL, we conduct experiments over several data d"},"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":"2012.02447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:04:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"01fa11b6fc718b051f913bfe32e9dd6bc7c63901f5f831ab73db02700b14aeb5","abstract_canon_sha256":"044c87a4631191ff51fb1b8f14d9c0905a64415e1473563b7ecea68f0ab39a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:59.680434Z","signature_b64":"tYxuRc69DfKnHXKjAWSPogcWY/gwx7oblSnoN4gN2XGVZ8UN/JdC7/HeX0JkjcU2p7uVXxZqZ2cZEAML6K1YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45c3e72d5d494931fce189e47763d4f41db2421677d27b4261f9c27d283a7470","last_reissued_at":"2026-07-05T01:56:59.679970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:59.679970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Bias in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annie Abay, Ebube Chuba, Heiko Ludwig, Nathalie Baracaldo, Shashank Rajamoni, Yi Zhou","submitted_at":"2020-12-04T08:04:12Z","abstract_excerpt":"As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train a global model without sharing their training data. In this paper, we discuss causes of bias in FL and propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy, a key FL requirement. As data heterogeneity among parties is one of the challenging characteristics of FL, we conduct experiments over several data d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02447","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/2012.02447/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":"2012.02447","created_at":"2026-07-05T01:56:59.680028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02447v1","created_at":"2026-07-05T01:56:59.680028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02447","created_at":"2026-07-05T01:56:59.680028+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXB6OLK5JFET","created_at":"2026-07-05T01:56:59.680028+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXB6OLK5JFETD7HB","created_at":"2026-07-05T01:56:59.680028+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXB6OLK5","created_at":"2026-07-05T01:56:59.680028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.16272","citing_title":"Incentivizing Honesty among Competitors in Collaborative Learning and Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21095","citing_title":"FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q","json":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q.json","graph_json":"https://pith.science/api/pith-number/IXB6OLK5JFETD7HBRHSHOY6U6Q/graph.json","events_json":"https://pith.science/api/pith-number/IXB6OLK5JFETD7HBRHSHOY6U6Q/events.json","paper":"https://pith.science/paper/IXB6OLK5"},"agent_actions":{"view_html":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q","download_json":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q.json","view_paper":"https://pith.science/paper/IXB6OLK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02447&json=true","fetch_graph":"https://pith.science/api/pith-number/IXB6OLK5JFETD7HBRHSHOY6U6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/IXB6OLK5JFETD7HBRHSHOY6U6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q/action/storage_attestation","attest_author":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q/action/author_attestation","sign_citation":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q/action/citation_signature","submit_replication":"https://pith.science/pith/IXB6OLK5JFETD7HBRHSHOY6U6Q/action/replication_record"}},"created_at":"2026-07-05T01:56:59.680028+00:00","updated_at":"2026-07-05T01:56:59.680028+00:00"}