{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5GXAELBMP5XI55IMN263VL2MIE","short_pith_number":"pith:5GXAELBM","schema_version":"1.0","canonical_sha256":"e9ae022c2c7f6e8ef50c6ebdbaaf4c4101599a4af1bd4fb5357d2d7e5b06c900","source":{"kind":"arxiv","id":"2406.04596","version":4},"attestation_state":"computed","paper":{"title":"Federated Representation Learning in the Under-Parameterized Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cong Shen, Jing Yang, Renpu Liu","submitted_at":"2024-06-07T03:00:07Z","abstract_excerpt":"Federated representation learning (FRL) is a popular personalized federated learning (FL) framework where clients work together to train a common representation while retaining their personalized heads. Existing studies, however, largely focus on the over-parameterized regime. In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models. We propose a novel FRL algorithm FLUTE, and theoretically characterize its sample complexity and convergence rate for linear models in t"},"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":"2406.04596","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T03:00:07Z","cross_cats_sorted":[],"title_canon_sha256":"dcff16315efb06cd43c7d96f68f32d1d4a975d6a22e7c62ebf78fdb7211e635c","abstract_canon_sha256":"78bb2634bb60b008e5fa002c96125e6f0950de68174d5a34b54180356bdf8777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:29.324676Z","signature_b64":"HnSskdf1YhK6pRJCX1HjoTSxbxLDL5kmMgERMLwEHpkPLzhVdIg5oHMEhLjQnbTcHozapx91sXnpjfYlV4EKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ae022c2c7f6e8ef50c6ebdbaaf4c4101599a4af1bd4fb5357d2d7e5b06c900","last_reissued_at":"2026-07-05T08:45:29.324264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:29.324264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Representation Learning in the Under-Parameterized Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cong Shen, Jing Yang, Renpu Liu","submitted_at":"2024-06-07T03:00:07Z","abstract_excerpt":"Federated representation learning (FRL) is a popular personalized federated learning (FL) framework where clients work together to train a common representation while retaining their personalized heads. Existing studies, however, largely focus on the over-parameterized regime. In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models. We propose a novel FRL algorithm FLUTE, and theoretically characterize its sample complexity and convergence rate for linear models in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04596","kind":"arxiv","version":4},"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/2406.04596/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":"2406.04596","created_at":"2026-07-05T08:45:29.324321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04596v4","created_at":"2026-07-05T08:45:29.324321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04596","created_at":"2026-07-05T08:45:29.324321+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GXAELBMP5XI","created_at":"2026-07-05T08:45:29.324321+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GXAELBMP5XI55IM","created_at":"2026-07-05T08:45:29.324321+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GXAELBM","created_at":"2026-07-05T08:45:29.324321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11912","citing_title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE","json":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE.json","graph_json":"https://pith.science/api/pith-number/5GXAELBMP5XI55IMN263VL2MIE/graph.json","events_json":"https://pith.science/api/pith-number/5GXAELBMP5XI55IMN263VL2MIE/events.json","paper":"https://pith.science/paper/5GXAELBM"},"agent_actions":{"view_html":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE","download_json":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE.json","view_paper":"https://pith.science/paper/5GXAELBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04596&json=true","fetch_graph":"https://pith.science/api/pith-number/5GXAELBMP5XI55IMN263VL2MIE/graph.json","fetch_events":"https://pith.science/api/pith-number/5GXAELBMP5XI55IMN263VL2MIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE/action/storage_attestation","attest_author":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE/action/author_attestation","sign_citation":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE/action/citation_signature","submit_replication":"https://pith.science/pith/5GXAELBMP5XI55IMN263VL2MIE/action/replication_record"}},"created_at":"2026-07-05T08:45:29.324321+00:00","updated_at":"2026-07-05T08:45:29.324321+00:00"}