{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OYLWAR7FAHSVGQ5C6YAT2SULI","short_pith_number":"pith:7OYLWAR7","schema_version":"1.0","canonical_sha256":"fbb0bb023f280f2a9a1d17b009ea545a06cb66533d203dede3b6883b2e45586a","source":{"kind":"arxiv","id":"2505.21877","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Hongyao Chen, Josef Kittler, Tianyang Xu, Xiaojun Wu","submitted_at":"2025-05-28T01:46:34Z","abstract_excerpt":"Batch Normalisation (BN) is widely used in conventional deep neural network training to harmonise the input-output distributions for each batch of data. However, federated learning, a distributed learning paradigm, faces the challenge of dealing with non-independent and identically distributed data among the client nodes. Due to the lack of a coherent methodology for updating BN statistical parameters, standard BN degrades the federated learning performance. To this end, it is urgent to explore an alternative normalisation solution for federated learning. In this work, we resolve the dilemma o"},"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":"2505.21877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T01:46:34Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"34ea087c48865d7baaceb9ba53ed4735564d794177bd58e988b36f5ca8270e8b","abstract_canon_sha256":"ebc2ba6850e4d26b7e73656d8c882a111a2dbdd2d2dfcf7a0c7464db3e495ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:23.099436Z","signature_b64":"v1kxaIJQjDIgfGO3WSSmwRtF7wwBHuWZAIP0eq3ULXYgG/4yECHkg8pEal+qp3MGe4WJ0pv/m0PWqkVNoM1nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb0bb023f280f2a9a1d17b009ea545a06cb66533d203dede3b6883b2e45586a","last_reissued_at":"2026-07-05T11:11:23.098936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:23.098936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Hongyao Chen, Josef Kittler, Tianyang Xu, Xiaojun Wu","submitted_at":"2025-05-28T01:46:34Z","abstract_excerpt":"Batch Normalisation (BN) is widely used in conventional deep neural network training to harmonise the input-output distributions for each batch of data. However, federated learning, a distributed learning paradigm, faces the challenge of dealing with non-independent and identically distributed data among the client nodes. Due to the lack of a coherent methodology for updating BN statistical parameters, standard BN degrades the federated learning performance. To this end, it is urgent to explore an alternative normalisation solution for federated learning. In this work, we resolve the dilemma o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21877","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/2505.21877/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":"2505.21877","created_at":"2026-07-05T11:11:23.098995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21877v1","created_at":"2026-07-05T11:11:23.098995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21877","created_at":"2026-07-05T11:11:23.098995+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OYLWAR7FAHS","created_at":"2026-07-05T11:11:23.098995+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OYLWAR7FAHSVGQ5","created_at":"2026-07-05T11:11:23.098995+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OYLWAR7","created_at":"2026-07-05T11:11:23.098995+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/7OYLWAR7FAHSVGQ5C6YAT2SULI","json":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI.json","graph_json":"https://pith.science/api/pith-number/7OYLWAR7FAHSVGQ5C6YAT2SULI/graph.json","events_json":"https://pith.science/api/pith-number/7OYLWAR7FAHSVGQ5C6YAT2SULI/events.json","paper":"https://pith.science/paper/7OYLWAR7"},"agent_actions":{"view_html":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI","download_json":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI.json","view_paper":"https://pith.science/paper/7OYLWAR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21877&json=true","fetch_graph":"https://pith.science/api/pith-number/7OYLWAR7FAHSVGQ5C6YAT2SULI/graph.json","fetch_events":"https://pith.science/api/pith-number/7OYLWAR7FAHSVGQ5C6YAT2SULI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI/action/storage_attestation","attest_author":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI/action/author_attestation","sign_citation":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI/action/citation_signature","submit_replication":"https://pith.science/pith/7OYLWAR7FAHSVGQ5C6YAT2SULI/action/replication_record"}},"created_at":"2026-07-05T11:11:23.098995+00:00","updated_at":"2026-07-05T11:11:23.098995+00:00"}