{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C3M4LX6OBKRTBMAPHEIKXHXBGR","short_pith_number":"pith:C3M4LX6O","schema_version":"1.0","canonical_sha256":"16d9c5dfce0aa330b00f3910ab9ee1345d35210f057dfb4606a76cc86716a157","source":{"kind":"arxiv","id":"2504.12025","version":1},"attestation_state":"computed","paper":{"title":"FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Lv, Qingfeng Du, Yu Zhang","submitted_at":"2025-04-16T12:32:37Z","abstract_excerpt":"Federated Learning (FL) enables decentralized model training across multiple parties while preserving privacy. However, most FL systems assume clients hold only unimodal data, limiting their real-world applicability, as institutions often possess multimodal data. Moreover, the lack of labeled data further constrains the performance of most FL methods. In this work, we propose FedEPA, a novel FL framework for multimodal learning. FedEPA employs a personalized local model aggregation strategy that leverages labeled data on clients to learn personalized aggregation weights, thereby alleviating th"},"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":"2504.12025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T12:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"7ed44a3731923fee93df01da6c6a2e6734bd7fe1e6bc33846d8a0caab5a41aad","abstract_canon_sha256":"05697cd331684c6f9f6f6f975323059e32021a1a16b26abe9148121c54748b91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:01.601537Z","signature_b64":"WQC51LIS4SUXOTOR6UIWZRaVdO0IlYzblaNrmufTfNw6MPz38gljmA8lKpAmzlAKswK+H5qjI1p7eScXiHMtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d9c5dfce0aa330b00f3910ab9ee1345d35210f057dfb4606a76cc86716a157","last_reissued_at":"2026-07-05T10:50:01.601042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:01.601042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Lv, Qingfeng Du, Yu Zhang","submitted_at":"2025-04-16T12:32:37Z","abstract_excerpt":"Federated Learning (FL) enables decentralized model training across multiple parties while preserving privacy. However, most FL systems assume clients hold only unimodal data, limiting their real-world applicability, as institutions often possess multimodal data. Moreover, the lack of labeled data further constrains the performance of most FL methods. In this work, we propose FedEPA, a novel FL framework for multimodal learning. FedEPA employs a personalized local model aggregation strategy that leverages labeled data on clients to learn personalized aggregation weights, thereby alleviating th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12025","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/2504.12025/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":"2504.12025","created_at":"2026-07-05T10:50:01.601108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12025v1","created_at":"2026-07-05T10:50:01.601108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12025","created_at":"2026-07-05T10:50:01.601108+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3M4LX6OBKRT","created_at":"2026-07-05T10:50:01.601108+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3M4LX6OBKRTBMAP","created_at":"2026-07-05T10:50:01.601108+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3M4LX6O","created_at":"2026-07-05T10:50:01.601108+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/C3M4LX6OBKRTBMAPHEIKXHXBGR","json":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR.json","graph_json":"https://pith.science/api/pith-number/C3M4LX6OBKRTBMAPHEIKXHXBGR/graph.json","events_json":"https://pith.science/api/pith-number/C3M4LX6OBKRTBMAPHEIKXHXBGR/events.json","paper":"https://pith.science/paper/C3M4LX6O"},"agent_actions":{"view_html":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR","download_json":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR.json","view_paper":"https://pith.science/paper/C3M4LX6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12025&json=true","fetch_graph":"https://pith.science/api/pith-number/C3M4LX6OBKRTBMAPHEIKXHXBGR/graph.json","fetch_events":"https://pith.science/api/pith-number/C3M4LX6OBKRTBMAPHEIKXHXBGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR/action/storage_attestation","attest_author":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR/action/author_attestation","sign_citation":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR/action/citation_signature","submit_replication":"https://pith.science/pith/C3M4LX6OBKRTBMAPHEIKXHXBGR/action/replication_record"}},"created_at":"2026-07-05T10:50:01.601108+00:00","updated_at":"2026-07-05T10:50:01.601108+00:00"}