{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XUS5SGDVHICKYIIN473ZWXMHI","short_pith_number":"pith:5XUS5SGD","schema_version":"1.0","canonical_sha256":"ede92ec8c3a9d02561086f3fbcdaec3a0aa6e8f24efb9d998114d04979f1980a","source":{"kind":"arxiv","id":"2404.15598","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning with Only Positive Labels by Exploring Label Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Du, Dacheng Tao, Dui Wang, Han Hu, Li Shen, Xuming An, Yonggang Wen, Yong Luo","submitted_at":"2024-04-24T02:22:50Z","abstract_excerpt":"Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data w.r.t. a single class label are provided for each client. This issue can be addressed by adding a specially designed regularizer on the server-side. Although effective sometimes, the label correlations are simply ignored and thus sub-optimal performance may be obtained. "},"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":"2404.15598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T02:22:50Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"042a9623e25d4ce3ad3dc33b684e6fcb5e563e8afb9919b823dd2eafdc26deab","abstract_canon_sha256":"0ae353b470065d1290fca0e39a1c5ddcaf02ec85154370aa1ba584ebce17c87b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:30.319865Z","signature_b64":"asB9a1nys/DrPrwWGFa00VNEO+VJUoFZ/F71/hWLsenn3uSXOaDMhyxi9SDmP4xZhz1zAwJjzrNPqjHm6zxNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede92ec8c3a9d02561086f3fbcdaec3a0aa6e8f24efb9d998114d04979f1980a","last_reissued_at":"2026-07-05T08:11:30.319349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:30.319349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Only Positive Labels by Exploring Label Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Du, Dacheng Tao, Dui Wang, Han Hu, Li Shen, Xuming An, Yonggang Wen, Yong Luo","submitted_at":"2024-04-24T02:22:50Z","abstract_excerpt":"Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data w.r.t. a single class label are provided for each client. This issue can be addressed by adding a specially designed regularizer on the server-side. Although effective sometimes, the label correlations are simply ignored and thus sub-optimal performance may be obtained. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15598","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/2404.15598/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":"2404.15598","created_at":"2026-07-05T08:11:30.319411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15598v1","created_at":"2026-07-05T08:11:30.319411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15598","created_at":"2026-07-05T08:11:30.319411+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XUS5SGDVHIC","created_at":"2026-07-05T08:11:30.319411+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XUS5SGDVHICKYII","created_at":"2026-07-05T08:11:30.319411+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XUS5SGD","created_at":"2026-07-05T08:11:30.319411+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/5XUS5SGDVHICKYIIN473ZWXMHI","json":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI.json","graph_json":"https://pith.science/api/pith-number/5XUS5SGDVHICKYIIN473ZWXMHI/graph.json","events_json":"https://pith.science/api/pith-number/5XUS5SGDVHICKYIIN473ZWXMHI/events.json","paper":"https://pith.science/paper/5XUS5SGD"},"agent_actions":{"view_html":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI","download_json":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI.json","view_paper":"https://pith.science/paper/5XUS5SGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15598&json=true","fetch_graph":"https://pith.science/api/pith-number/5XUS5SGDVHICKYIIN473ZWXMHI/graph.json","fetch_events":"https://pith.science/api/pith-number/5XUS5SGDVHICKYIIN473ZWXMHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI/action/storage_attestation","attest_author":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI/action/author_attestation","sign_citation":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI/action/citation_signature","submit_replication":"https://pith.science/pith/5XUS5SGDVHICKYIIN473ZWXMHI/action/replication_record"}},"created_at":"2026-07-05T08:11:30.319411+00:00","updated_at":"2026-07-05T08:11:30.319411+00:00"}