{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YSXLTWJA3PCALP5DHTGKAPUP44","short_pith_number":"pith:YSXLTWJA","schema_version":"1.0","canonical_sha256":"c4aeb9d920dbc405bfa33ccca03e8fe70d2087f2f668fb8038e8d23273b2b1c6","source":{"kind":"arxiv","id":"2410.02006","version":2},"attestation_state":"computed","paper":{"title":"An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Giacomo Tarroni, Jonathan Passerat-Palmbach, Vasilis Siomos","submitted_at":"2024-10-02T20:16:56Z","abstract_excerpt":"Federated learning is a decentralized collaborative training paradigm preserving stakeholders' data ownership while improving performance and generalization. However, statistical heterogeneity among client datasets degrades system performance. To address this issue, we propose Adaptive Normalization-free Feature Recalibration (ANFR), a model architecture-level approach that combines weight standardization and channel attention to combat heterogeneous data in FL. ANFR leverages weight standardization to avoid mismatched client statistics and inconsistent averaging, ensuring robustness under het"},"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":"2410.02006","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T20:16:56Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3b34ad1337e4e42953945a6b9498b31a894b1b49b07b12cc3847889172f42061","abstract_canon_sha256":"4513e50b0d392b9eab5164f0a041e372c9a9d2e574192fb06fb5b1bfe49691a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:02.167261Z","signature_b64":"lg5nO63HdezUEQqC0GlyGB6GwxHYNNLOK1LP9IWgBnAczQlxc3FwzEhKozvdnYk+DCT+rteeuzOjzgJjCrcTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4aeb9d920dbc405bfa33ccca03e8fe70d2087f2f668fb8038e8d23273b2b1c6","last_reissued_at":"2026-07-05T12:06:02.166762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:02.166762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Giacomo Tarroni, Jonathan Passerat-Palmbach, Vasilis Siomos","submitted_at":"2024-10-02T20:16:56Z","abstract_excerpt":"Federated learning is a decentralized collaborative training paradigm preserving stakeholders' data ownership while improving performance and generalization. However, statistical heterogeneity among client datasets degrades system performance. To address this issue, we propose Adaptive Normalization-free Feature Recalibration (ANFR), a model architecture-level approach that combines weight standardization and channel attention to combat heterogeneous data in FL. ANFR leverages weight standardization to avoid mismatched client statistics and inconsistent averaging, ensuring robustness under het"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02006","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/2410.02006/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":"2410.02006","created_at":"2026-07-05T12:06:02.166821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02006v2","created_at":"2026-07-05T12:06:02.166821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02006","created_at":"2026-07-05T12:06:02.166821+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSXLTWJA3PCA","created_at":"2026-07-05T12:06:02.166821+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSXLTWJA3PCALP5D","created_at":"2026-07-05T12:06:02.166821+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSXLTWJA","created_at":"2026-07-05T12:06:02.166821+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/YSXLTWJA3PCALP5DHTGKAPUP44","json":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44.json","graph_json":"https://pith.science/api/pith-number/YSXLTWJA3PCALP5DHTGKAPUP44/graph.json","events_json":"https://pith.science/api/pith-number/YSXLTWJA3PCALP5DHTGKAPUP44/events.json","paper":"https://pith.science/paper/YSXLTWJA"},"agent_actions":{"view_html":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44","download_json":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44.json","view_paper":"https://pith.science/paper/YSXLTWJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02006&json=true","fetch_graph":"https://pith.science/api/pith-number/YSXLTWJA3PCALP5DHTGKAPUP44/graph.json","fetch_events":"https://pith.science/api/pith-number/YSXLTWJA3PCALP5DHTGKAPUP44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44/action/storage_attestation","attest_author":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44/action/author_attestation","sign_citation":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44/action/citation_signature","submit_replication":"https://pith.science/pith/YSXLTWJA3PCALP5DHTGKAPUP44/action/replication_record"}},"created_at":"2026-07-05T12:06:02.166821+00:00","updated_at":"2026-07-05T12:06:02.166821+00:00"}