{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WUPDPIWT6EHDWK2J35ZS37RTOE","short_pith_number":"pith:WUPDPIWT","schema_version":"1.0","canonical_sha256":"b51e37a2d3f10e3b2b49df732dfe33713b5c4ceff86d2be31c64e69e1528152b","source":{"kind":"arxiv","id":"2311.08202","version":1},"attestation_state":"computed","paper":{"title":"Federated Skewed Label Learning with Logits Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Gao, Hao Tan, Min Liu, Runhan Li, Sheng Sun, Xuefeng Jiang, Yuwei Wang, Zhiyuan Wu","submitted_at":"2023-11-14T14:37:33Z","abstract_excerpt":"Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in realistic FL settings, as it causes significant performance deterioration due to discrepancies in optimization among local models. In this work, we focus on label distribution skew, a common scenario in data heterogeneity, where the data label categories are imbalanced on each client. To address this issue, we propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Speci"},"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":"2311.08202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T14:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"876be67736d4913332af9829eb8d454d9f22acbafabe1b1396b0e6ea57b0b72d","abstract_canon_sha256":"a384ef79d6ce1d37c007dcbed2a6391b50b6328b607d3cb024223a96cb784b64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:41.696367Z","signature_b64":"v5L3M1C++JvY9y8eWudszrQIf4Dqnl6e8vAW/pKd/gzN8YEhPtTMKB0rJP2iTrnNAgsfpJ49zLQYinS8N4TfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b51e37a2d3f10e3b2b49df732dfe33713b5c4ceff86d2be31c64e69e1528152b","last_reissued_at":"2026-07-05T07:12:41.695891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:41.695891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Skewed Label Learning with Logits Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Gao, Hao Tan, Min Liu, Runhan Li, Sheng Sun, Xuefeng Jiang, Yuwei Wang, Zhiyuan Wu","submitted_at":"2023-11-14T14:37:33Z","abstract_excerpt":"Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in realistic FL settings, as it causes significant performance deterioration due to discrepancies in optimization among local models. In this work, we focus on label distribution skew, a common scenario in data heterogeneity, where the data label categories are imbalanced on each client. To address this issue, we propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08202","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/2311.08202/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":"2311.08202","created_at":"2026-07-05T07:12:41.695949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08202v1","created_at":"2026-07-05T07:12:41.695949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08202","created_at":"2026-07-05T07:12:41.695949+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUPDPIWT6EHD","created_at":"2026-07-05T07:12:41.695949+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUPDPIWT6EHDWK2J","created_at":"2026-07-05T07:12:41.695949+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUPDPIWT","created_at":"2026-07-05T07:12:41.695949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02079","citing_title":"Robust Federated Learning against Noisy Clients via Masked Optimization","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE","json":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE.json","graph_json":"https://pith.science/api/pith-number/WUPDPIWT6EHDWK2J35ZS37RTOE/graph.json","events_json":"https://pith.science/api/pith-number/WUPDPIWT6EHDWK2J35ZS37RTOE/events.json","paper":"https://pith.science/paper/WUPDPIWT"},"agent_actions":{"view_html":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE","download_json":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE.json","view_paper":"https://pith.science/paper/WUPDPIWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08202&json=true","fetch_graph":"https://pith.science/api/pith-number/WUPDPIWT6EHDWK2J35ZS37RTOE/graph.json","fetch_events":"https://pith.science/api/pith-number/WUPDPIWT6EHDWK2J35ZS37RTOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE/action/storage_attestation","attest_author":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE/action/author_attestation","sign_citation":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE/action/citation_signature","submit_replication":"https://pith.science/pith/WUPDPIWT6EHDWK2J35ZS37RTOE/action/replication_record"}},"created_at":"2026-07-05T07:12:41.695949+00:00","updated_at":"2026-07-05T07:12:41.695949+00:00"}