{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DO7FRY6TEHOOGCC7E6MMV5BDFO","short_pith_number":"pith:DO7FRY6T","schema_version":"1.0","canonical_sha256":"1bbe58e3d321dce3085f2798caf4232b9962a8b2a35a8dd83da530004d9ee0d1","source":{"kind":"arxiv","id":"2504.21775","version":1},"attestation_state":"computed","paper":{"title":"Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ming Tang, Rongguang Ye","submitted_at":"2025-04-30T16:25:02Z","abstract_excerpt":"Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fairness to preference-specifc models on the trade-off curve, known as local Pareto front. However, existing methods typically adopt a uniform preference sampling distribution to train the hypernet across clients, neglecting the inherent heterogeneity of their local Pareto fronts. Meanwhile, from the perspective of generalization, they do not consider the gap between local and global Pareto fronts on the global dataset"},"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":"2504.21775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T16:25:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6eaa272623f32c41843f72a190cbec5c2320436795d880145136afdb2c546c87","abstract_canon_sha256":"db5c0d254a1c36b7f78b64265d47c673fab44c5d6bc3bd27009fed92c19f7430"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:29.373279Z","signature_b64":"il9f/ntbHuo1u+UErwfAL5eyBSR8sOkh6Ug7Xp+reODKLlIzfj6eeMtZdVAV5N3ZPgcnjyknUu5LG+Rg40W7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bbe58e3d321dce3085f2798caf4232b9962a8b2a35a8dd83da530004d9ee0d1","last_reissued_at":"2026-07-05T10:56:29.372815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:29.372815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ming Tang, Rongguang Ye","submitted_at":"2025-04-30T16:25:02Z","abstract_excerpt":"Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fairness to preference-specifc models on the trade-off curve, known as local Pareto front. However, existing methods typically adopt a uniform preference sampling distribution to train the hypernet across clients, neglecting the inherent heterogeneity of their local Pareto fronts. Meanwhile, from the perspective of generalization, they do not consider the gap between local and global Pareto fronts on the global dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21775","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/2504.21775/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":"2504.21775","created_at":"2026-07-05T10:56:29.372864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21775v1","created_at":"2026-07-05T10:56:29.372864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21775","created_at":"2026-07-05T10:56:29.372864+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO7FRY6TEHOO","created_at":"2026-07-05T10:56:29.372864+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO7FRY6TEHOOGCC7","created_at":"2026-07-05T10:56:29.372864+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO7FRY6T","created_at":"2026-07-05T10:56:29.372864+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/DO7FRY6TEHOOGCC7E6MMV5BDFO","json":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO.json","graph_json":"https://pith.science/api/pith-number/DO7FRY6TEHOOGCC7E6MMV5BDFO/graph.json","events_json":"https://pith.science/api/pith-number/DO7FRY6TEHOOGCC7E6MMV5BDFO/events.json","paper":"https://pith.science/paper/DO7FRY6T"},"agent_actions":{"view_html":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO","download_json":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO.json","view_paper":"https://pith.science/paper/DO7FRY6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21775&json=true","fetch_graph":"https://pith.science/api/pith-number/DO7FRY6TEHOOGCC7E6MMV5BDFO/graph.json","fetch_events":"https://pith.science/api/pith-number/DO7FRY6TEHOOGCC7E6MMV5BDFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO/action/storage_attestation","attest_author":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO/action/author_attestation","sign_citation":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO/action/citation_signature","submit_replication":"https://pith.science/pith/DO7FRY6TEHOOGCC7E6MMV5BDFO/action/replication_record"}},"created_at":"2026-07-05T10:56:29.372864+00:00","updated_at":"2026-07-05T10:56:29.372864+00:00"}