{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6LQINDY3MXJO6M6Q23GU2FA6JO","short_pith_number":"pith:6LQINDY3","schema_version":"1.0","canonical_sha256":"f2e0868f1b65d2ef33d0d6cd4d141e4bad401e3342b2e93646f46db7bb06af05","source":{"kind":"arxiv","id":"2411.03799","version":2},"attestation_state":"computed","paper":{"title":"Overcoming label shift with target-aware federated learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Breitholtz, Edvin Listo Zec, Fredrik D. Johansson","submitted_at":"2024-11-06T09:52:45Z","abstract_excerpt":"Federated learning enables multiple actors to collaboratively train models without sharing private data. Existing algorithms are successful and well-justified in this task when the intended target domain, where the trained model will be used, shares data distribution with the aggregate of clients, but this is often violated in practice. A common reason is label shift -- that the label distributions differ between clients and the target domain. We demonstrate empirically that this can significantly degrade performance. To address this problem, we propose FedPALS, a principled and practical mode"},"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":"2411.03799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T09:52:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fdc1966537fd97e36b870e4e334e70ef575f7053fe02df3e2d4d7c56d429775","abstract_canon_sha256":"df1ec28b6d350992df22d3d1bf58c0b8e24edd821aa0e5895484b02ddcf9e9cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:08.890647Z","signature_b64":"/EuDrwClGZVle3CeZ3jkGWYm/SJJMJPUff9UoW1Zcgc1UGxr/V11c39Kyvd9cJpZctBxsD3bZ0ba72BBr5CyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e0868f1b65d2ef33d0d6cd4d141e4bad401e3342b2e93646f46db7bb06af05","last_reissued_at":"2026-07-05T11:59:08.890215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:08.890215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming label shift with target-aware federated learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Breitholtz, Edvin Listo Zec, Fredrik D. Johansson","submitted_at":"2024-11-06T09:52:45Z","abstract_excerpt":"Federated learning enables multiple actors to collaboratively train models without sharing private data. Existing algorithms are successful and well-justified in this task when the intended target domain, where the trained model will be used, shares data distribution with the aggregate of clients, but this is often violated in practice. A common reason is label shift -- that the label distributions differ between clients and the target domain. We demonstrate empirically that this can significantly degrade performance. To address this problem, we propose FedPALS, a principled and practical mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03799","kind":"arxiv","version":2},"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/2411.03799/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":"2411.03799","created_at":"2026-07-05T11:59:08.890267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03799v2","created_at":"2026-07-05T11:59:08.890267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03799","created_at":"2026-07-05T11:59:08.890267+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LQINDY3MXJO","created_at":"2026-07-05T11:59:08.890267+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LQINDY3MXJO6M6Q","created_at":"2026-07-05T11:59:08.890267+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LQINDY3","created_at":"2026-07-05T11:59:08.890267+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/6LQINDY3MXJO6M6Q23GU2FA6JO","json":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO.json","graph_json":"https://pith.science/api/pith-number/6LQINDY3MXJO6M6Q23GU2FA6JO/graph.json","events_json":"https://pith.science/api/pith-number/6LQINDY3MXJO6M6Q23GU2FA6JO/events.json","paper":"https://pith.science/paper/6LQINDY3"},"agent_actions":{"view_html":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO","download_json":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO.json","view_paper":"https://pith.science/paper/6LQINDY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03799&json=true","fetch_graph":"https://pith.science/api/pith-number/6LQINDY3MXJO6M6Q23GU2FA6JO/graph.json","fetch_events":"https://pith.science/api/pith-number/6LQINDY3MXJO6M6Q23GU2FA6JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO/action/storage_attestation","attest_author":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO/action/author_attestation","sign_citation":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO/action/citation_signature","submit_replication":"https://pith.science/pith/6LQINDY3MXJO6M6Q23GU2FA6JO/action/replication_record"}},"created_at":"2026-07-05T11:59:08.890267+00:00","updated_at":"2026-07-05T11:59:08.890267+00:00"}