{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZGGT4545NW375NQAF4Q6TIWMXE","short_pith_number":"pith:ZGGT4545","schema_version":"1.0","canonical_sha256":"c98d3e779d6db7feb6002f21e9a2ccb9382c7057ba25e289e3f8f9b65ffbdbfa","source":{"kind":"arxiv","id":"2102.07623","version":2},"attestation_state":"computed","paper":{"title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meirui Jiang, Michael Kamp, Qi Dou, Xiaofei Zhang, Xiaoxiao Li","submitted_at":"2021-02-15T16:04:10Z","abstract_excerpt":"The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of independent and identically distributed samples across local clients does not hold for federated learning setups. Under this setting, neural network training performance may vary significantly according to the data distribution and even hurt training convergence. Most of the previous work has focused on a difference in the distribution of labels or client shifts. Unl"},"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":"2102.07623","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T16:04:10Z","cross_cats_sorted":[],"title_canon_sha256":"186aa3fe42ad69096a309a3db44d5360fad0f42c217e4b5491cff674f60d23b7","abstract_canon_sha256":"9fe0832793d43c32572cb5a7061e4dd165f49adb0bb970d82dac3a1154b6662b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:14.615807Z","signature_b64":"V8Kagsqn6ytM8Sk5NQVVi8cQgrgG2yWqrTj5XERGl8PD/wgk9D4JA2JMFfnSsdUiIBVfphmaYc5ZTQ6I9eT0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98d3e779d6db7feb6002f21e9a2ccb9382c7057ba25e289e3f8f9b65ffbdbfa","last_reissued_at":"2026-07-05T02:39:14.615234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:14.615234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meirui Jiang, Michael Kamp, Qi Dou, Xiaofei Zhang, Xiaoxiao Li","submitted_at":"2021-02-15T16:04:10Z","abstract_excerpt":"The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of independent and identically distributed samples across local clients does not hold for federated learning setups. Under this setting, neural network training performance may vary significantly according to the data distribution and even hurt training convergence. Most of the previous work has focused on a difference in the distribution of labels or client shifts. Unl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07623","kind":"arxiv","version":2},"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/2102.07623/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":"2102.07623","created_at":"2026-07-05T02:39:14.615305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07623v2","created_at":"2026-07-05T02:39:14.615305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07623","created_at":"2026-07-05T02:39:14.615305+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGGT4545NW37","created_at":"2026-07-05T02:39:14.615305+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGGT4545NW375NQA","created_at":"2026-07-05T02:39:14.615305+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGGT4545","created_at":"2026-07-05T02:39:14.615305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01272","citing_title":"Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00656","citing_title":"Demystifying the Optimal Fair Classifier in Multi-Class Classification","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23334","citing_title":"Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05957","citing_title":"Domain-Adaptive Model Merging Across Disconnected Modes","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22494","citing_title":"FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02337","citing_title":"FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00322","citing_title":"Federated Weather Modeling on Sensor Data","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00892","citing_title":"When To Adapt? Adapting the Model or Data in Federated Medical Imaging","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06727","citing_title":"Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19118","citing_title":"DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE","json":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE.json","graph_json":"https://pith.science/api/pith-number/ZGGT4545NW375NQAF4Q6TIWMXE/graph.json","events_json":"https://pith.science/api/pith-number/ZGGT4545NW375NQAF4Q6TIWMXE/events.json","paper":"https://pith.science/paper/ZGGT4545"},"agent_actions":{"view_html":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE","download_json":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE.json","view_paper":"https://pith.science/paper/ZGGT4545","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07623&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGGT4545NW375NQAF4Q6TIWMXE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGGT4545NW375NQAF4Q6TIWMXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE/action/storage_attestation","attest_author":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE/action/author_attestation","sign_citation":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE/action/citation_signature","submit_replication":"https://pith.science/pith/ZGGT4545NW375NQAF4Q6TIWMXE/action/replication_record"}},"created_at":"2026-07-05T02:39:14.615305+00:00","updated_at":"2026-07-05T02:39:14.615305+00:00"}