{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OVJ4M3LPSBBHOZ3Y4G6LTWSPQK","short_pith_number":"pith:OVJ4M3LP","schema_version":"1.0","canonical_sha256":"7553c66d6f9042776778e1bcb9da4f82b0c3cddfd2e6bae8476dc0c4305b9dd0","source":{"kind":"arxiv","id":"2301.02982","version":3},"attestation_state":"computed","paper":{"title":"Why Batch Normalization Damage Federated Learning on Non-IID Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Qingjiang Shi, Tsung-Hui Chang, Yanmeng Wang","submitted_at":"2023-01-08T05:24:12Z","abstract_excerpt":"As a promising distributed learning paradigm, federated learning (FL) involves training deep neural network (DNN) models at the network edge while protecting the privacy of the edge clients. To train a large-scale DNN model, batch normalization (BN) has been regarded as a simple and effective means to accelerate the training and improve the generalization capability. However, recent findings indicate that BN can significantly impair the performance of FL in the presence of non-i.i.d. data. While several FL algorithms have been proposed to address this issue, their performance still falls signi"},"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":"2301.02982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-08T05:24:12Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"1e18043c3d4fc5943a01f922db3e9b32783afb8aca61c7a7a69718b223d26a28","abstract_canon_sha256":"1fe83fc9e30bd46a9d9d46ad2c1f6d824c025203f8dabbf2cb9f2979d58afd84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:45.739844Z","signature_b64":"FafLQdfu0+RMUiws189GB7SjTxaJva3Nzc+/jFmnzV7NNp217AoEvmke0SWc/1l0i7qEMqfWKVvhI7pAB3VqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7553c66d6f9042776778e1bcb9da4f82b0c3cddfd2e6bae8476dc0c4305b9dd0","last_reissued_at":"2026-07-05T07:10:45.739403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:45.739403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Batch Normalization Damage Federated Learning on Non-IID Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Qingjiang Shi, Tsung-Hui Chang, Yanmeng Wang","submitted_at":"2023-01-08T05:24:12Z","abstract_excerpt":"As a promising distributed learning paradigm, federated learning (FL) involves training deep neural network (DNN) models at the network edge while protecting the privacy of the edge clients. To train a large-scale DNN model, batch normalization (BN) has been regarded as a simple and effective means to accelerate the training and improve the generalization capability. However, recent findings indicate that BN can significantly impair the performance of FL in the presence of non-i.i.d. data. While several FL algorithms have been proposed to address this issue, their performance still falls signi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02982","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/2301.02982/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":"2301.02982","created_at":"2026-07-05T07:10:45.739454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02982v3","created_at":"2026-07-05T07:10:45.739454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02982","created_at":"2026-07-05T07:10:45.739454+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVJ4M3LPSBBH","created_at":"2026-07-05T07:10:45.739454+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVJ4M3LPSBBHOZ3Y","created_at":"2026-07-05T07:10:45.739454+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVJ4M3LP","created_at":"2026-07-05T07:10:45.739454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03092","citing_title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK","json":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK.json","graph_json":"https://pith.science/api/pith-number/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/graph.json","events_json":"https://pith.science/api/pith-number/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/events.json","paper":"https://pith.science/paper/OVJ4M3LP"},"agent_actions":{"view_html":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK","download_json":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK.json","view_paper":"https://pith.science/paper/OVJ4M3LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02982&json=true","fetch_graph":"https://pith.science/api/pith-number/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/graph.json","fetch_events":"https://pith.science/api/pith-number/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/action/storage_attestation","attest_author":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/action/author_attestation","sign_citation":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/action/citation_signature","submit_replication":"https://pith.science/pith/OVJ4M3LPSBBHOZ3Y4G6LTWSPQK/action/replication_record"}},"created_at":"2026-07-05T07:10:45.739454+00:00","updated_at":"2026-07-05T07:10:45.739454+00:00"}