{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UW2ROLFUSYT6SJOVGKHJPQ33ED","short_pith_number":"pith:UW2ROLFU","schema_version":"1.0","canonical_sha256":"a5b5172cb49627e925d5328e97c37b20d6538d337b83218b3afdd7f2d39bb92c","source":{"kind":"arxiv","id":"2403.03333","version":4},"attestation_state":"computed","paper":{"title":"Federated Learning over Connected Modes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dennis Grinwald, Philipp Wiesner, Shinichi Nakajima","submitted_at":"2024-03-05T21:34:23Z","abstract_excerpt":"Statistical heterogeneity in federated learning poses two major challenges: slow global training due to conflicting gradient signals, and the need of personalization for local distributions. In this work, we tackle both challenges by leveraging recent advances in \\emph{linear mode connectivity} -- identifying a linearly connected low-loss region in the parameter space of neural networks, which we call solution simplex. We propose federated learning over connected modes (\\textsc{Floco}), where clients are assigned local subregions in this simplex based on their gradient signals, and together le"},"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":"2403.03333","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-05T21:34:23Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"bc18769ffd5533ed840fe44f5a1c25de936766e90eded5fabcca6911be904c54","abstract_canon_sha256":"da6d3b45ac7b7d778fa68bd7142ca90252ce0433c7c39a33216e4ab18ac1a7ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:58.798302Z","signature_b64":"WMjNVFADYAdRn1IU+uYvmZRXj+Qv1dyOndIvbOzQeTC1m8jmAJw7uaFDFTpLaKho85wzcO9CmWglw19fvRNhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5b5172cb49627e925d5328e97c37b20d6538d337b83218b3afdd7f2d39bb92c","last_reissued_at":"2026-07-05T10:12:58.797783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:58.797783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning over Connected Modes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dennis Grinwald, Philipp Wiesner, Shinichi Nakajima","submitted_at":"2024-03-05T21:34:23Z","abstract_excerpt":"Statistical heterogeneity in federated learning poses two major challenges: slow global training due to conflicting gradient signals, and the need of personalization for local distributions. In this work, we tackle both challenges by leveraging recent advances in \\emph{linear mode connectivity} -- identifying a linearly connected low-loss region in the parameter space of neural networks, which we call solution simplex. We propose federated learning over connected modes (\\textsc{Floco}), where clients are assigned local subregions in this simplex based on their gradient signals, and together le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03333","kind":"arxiv","version":4},"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/2403.03333/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":"2403.03333","created_at":"2026-07-05T10:12:58.797838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03333v4","created_at":"2026-07-05T10:12:58.797838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03333","created_at":"2026-07-05T10:12:58.797838+00:00"},{"alias_kind":"pith_short_12","alias_value":"UW2ROLFUSYT6","created_at":"2026-07-05T10:12:58.797838+00:00"},{"alias_kind":"pith_short_16","alias_value":"UW2ROLFUSYT6SJOV","created_at":"2026-07-05T10:12:58.797838+00:00"},{"alias_kind":"pith_short_8","alias_value":"UW2ROLFU","created_at":"2026-07-05T10:12:58.797838+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/UW2ROLFUSYT6SJOVGKHJPQ33ED","json":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED.json","graph_json":"https://pith.science/api/pith-number/UW2ROLFUSYT6SJOVGKHJPQ33ED/graph.json","events_json":"https://pith.science/api/pith-number/UW2ROLFUSYT6SJOVGKHJPQ33ED/events.json","paper":"https://pith.science/paper/UW2ROLFU"},"agent_actions":{"view_html":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED","download_json":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED.json","view_paper":"https://pith.science/paper/UW2ROLFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03333&json=true","fetch_graph":"https://pith.science/api/pith-number/UW2ROLFUSYT6SJOVGKHJPQ33ED/graph.json","fetch_events":"https://pith.science/api/pith-number/UW2ROLFUSYT6SJOVGKHJPQ33ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED/action/storage_attestation","attest_author":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED/action/author_attestation","sign_citation":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED/action/citation_signature","submit_replication":"https://pith.science/pith/UW2ROLFUSYT6SJOVGKHJPQ33ED/action/replication_record"}},"created_at":"2026-07-05T10:12:58.797838+00:00","updated_at":"2026-07-05T10:12:58.797838+00:00"}