{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VGJQTHXTKCOBFNDX7HX6L6LI3G","short_pith_number":"pith:VGJQTHXT","schema_version":"1.0","canonical_sha256":"a993099ef3509c12b477f9efe5f968d99a695fa1cd101c83c1ab75e2516df4dc","source":{"kind":"arxiv","id":"2406.01116","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Heterogeneous Federated Learning with Closed-form Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Barbara Caputo, Eros Fan\\`i, Marco Ciccone, Raffaello Camoriano","submitted_at":"2024-06-03T08:52:06Z","abstract_excerpt":"Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively impacting convergence speed and accuracy. To address this issue, we introduce Federated Recursive Ridge Regression (Fed3R). Our method fits a Ridge Regression classifier computed in closed form leveraging pre-trained features. Fed3R is immune to statistical heterogeneity and is invariant to the sampling order of the clients. Therefore, it proves parti"},"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":"2406.01116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T08:52:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"de2b7728107d59931f19794398b9295ff60789218c401f1197a5fe6e70b5c68a","abstract_canon_sha256":"cea86c8bc08fe984afaee6ab93cb4307cce11a45379d82337d78d49a1dfcbca2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:35.395481Z","signature_b64":"IV9GqkK18aJgQ0WbTzm2na5TEdfNVMNFULjoUWG+Gv/LVhalwuCQ5onxincFAOg8HhArQgYoV61BH0UbGY4VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a993099ef3509c12b477f9efe5f968d99a695fa1cd101c83c1ab75e2516df4dc","last_reissued_at":"2026-07-05T08:26:35.395017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:35.395017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Heterogeneous Federated Learning with Closed-form Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Barbara Caputo, Eros Fan\\`i, Marco Ciccone, Raffaello Camoriano","submitted_at":"2024-06-03T08:52:06Z","abstract_excerpt":"Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively impacting convergence speed and accuracy. To address this issue, we introduce Federated Recursive Ridge Regression (Fed3R). Our method fits a Ridge Regression classifier computed in closed form leveraging pre-trained features. Fed3R is immune to statistical heterogeneity and is invariant to the sampling order of the clients. Therefore, it proves parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01116","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/2406.01116/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":"2406.01116","created_at":"2026-07-05T08:26:35.395072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01116v1","created_at":"2026-07-05T08:26:35.395072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01116","created_at":"2026-07-05T08:26:35.395072+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGJQTHXTKCOB","created_at":"2026-07-05T08:26:35.395072+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGJQTHXTKCOBFNDX","created_at":"2026-07-05T08:26:35.395072+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGJQTHXT","created_at":"2026-07-05T08:26:35.395072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11480","citing_title":"Accurate and Resource-Efficient Federated Continual Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G","json":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G.json","graph_json":"https://pith.science/api/pith-number/VGJQTHXTKCOBFNDX7HX6L6LI3G/graph.json","events_json":"https://pith.science/api/pith-number/VGJQTHXTKCOBFNDX7HX6L6LI3G/events.json","paper":"https://pith.science/paper/VGJQTHXT"},"agent_actions":{"view_html":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G","download_json":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G.json","view_paper":"https://pith.science/paper/VGJQTHXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01116&json=true","fetch_graph":"https://pith.science/api/pith-number/VGJQTHXTKCOBFNDX7HX6L6LI3G/graph.json","fetch_events":"https://pith.science/api/pith-number/VGJQTHXTKCOBFNDX7HX6L6LI3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G/action/storage_attestation","attest_author":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G/action/author_attestation","sign_citation":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G/action/citation_signature","submit_replication":"https://pith.science/pith/VGJQTHXTKCOBFNDX7HX6L6LI3G/action/replication_record"}},"created_at":"2026-07-05T08:26:35.395072+00:00","updated_at":"2026-07-05T08:26:35.395072+00:00"}