{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y45BWYXDCRJU6WIF7TUA4MLX46","short_pith_number":"pith:Y45BWYXD","schema_version":"1.0","canonical_sha256":"c73a1b62e314534f5905fce80e3177e7ae432ae08db8d86e117fdf437464ffd1","source":{"kind":"arxiv","id":"2401.02329","version":3},"attestation_state":"computed","paper":{"title":"Exploring Vacant Classes in Label-Skewed Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Kuangpu Guo, Ran He, Tieniu Tan, Yuhe Ding, Zilei Wang","submitted_at":"2024-01-04T16:06:31Z","abstract_excerpt":"Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compare"},"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":"2401.02329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T16:06:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cc1b5d53382569bd18779352c81db8b6f863301529485f2c2dea7e98c1993fb2","abstract_canon_sha256":"1bf643301bf8ddcdd76956f0ae677db39fe4f3cc8595c0a89a4cf643881ddc13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:40.908529Z","signature_b64":"7cBLt6UdEZQdvoi3NpVquzx1HmOP629G27g3Zq+ZGLu79SATrrH3D11dPYMdAIEBq0SjciqoHcM7LZTMk0ccCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c73a1b62e314534f5905fce80e3177e7ae432ae08db8d86e117fdf437464ffd1","last_reissued_at":"2026-07-05T09:49:40.908081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:40.908081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Vacant Classes in Label-Skewed Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Kuangpu Guo, Ran He, Tieniu Tan, Yuhe Ding, Zilei Wang","submitted_at":"2024-01-04T16:06:31Z","abstract_excerpt":"Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compare"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02329","kind":"arxiv","version":3},"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/2401.02329/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":"2401.02329","created_at":"2026-07-05T09:49:40.908129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02329v3","created_at":"2026-07-05T09:49:40.908129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02329","created_at":"2026-07-05T09:49:40.908129+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y45BWYXDCRJU","created_at":"2026-07-05T09:49:40.908129+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y45BWYXDCRJU6WIF","created_at":"2026-07-05T09:49:40.908129+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y45BWYXD","created_at":"2026-07-05T09:49:40.908129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.07587","citing_title":"FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46","json":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46.json","graph_json":"https://pith.science/api/pith-number/Y45BWYXDCRJU6WIF7TUA4MLX46/graph.json","events_json":"https://pith.science/api/pith-number/Y45BWYXDCRJU6WIF7TUA4MLX46/events.json","paper":"https://pith.science/paper/Y45BWYXD"},"agent_actions":{"view_html":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46","download_json":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46.json","view_paper":"https://pith.science/paper/Y45BWYXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02329&json=true","fetch_graph":"https://pith.science/api/pith-number/Y45BWYXDCRJU6WIF7TUA4MLX46/graph.json","fetch_events":"https://pith.science/api/pith-number/Y45BWYXDCRJU6WIF7TUA4MLX46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46/action/storage_attestation","attest_author":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46/action/author_attestation","sign_citation":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46/action/citation_signature","submit_replication":"https://pith.science/pith/Y45BWYXDCRJU6WIF7TUA4MLX46/action/replication_record"}},"created_at":"2026-07-05T09:49:40.908129+00:00","updated_at":"2026-07-05T09:49:40.908129+00:00"}