{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L5RU4ZJOY5IE2WSBWKMC4JAMF3","short_pith_number":"pith:L5RU4ZJO","schema_version":"1.0","canonical_sha256":"5f634e652ec7504d5a41b2982e240c2ee31c8e5ba624d0cdb424d09720eb9c5f","source":{"kind":"arxiv","id":"2306.13263","version":2},"attestation_state":"computed","paper":{"title":"Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Bo Li, Mikkel N. Schmidt, Sebastian U. Stich, Tommy S. Alstr{\\o}m, Yasin Esfandiari","submitted_at":"2023-06-23T02:19:52Z","abstract_excerpt":"In federated learning, data heterogeneity is a critical challenge. A straightforward solution is to shuffle the clients' data to homogenize the distribution. However, this may violate data access rights, and how and when shuffling can accelerate the convergence of a federated optimization algorithm is not theoretically well understood. In this paper, we establish a precise and quantifiable correspondence between data heterogeneity and parameters in the convergence rate when a fraction of data is shuffled across clients. We prove that shuffling can quadratically reduce the gradient dissimilarit"},"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":"2306.13263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-23T02:19:52Z","cross_cats_sorted":["cs.CV","cs.DC"],"title_canon_sha256":"fa0bcc592e22906cb118304307e555c958105c042b703c8c6e4cb15e4999f2cf","abstract_canon_sha256":"37795d486dc69626d061d0ab3b187470f78895cf5defcd54664c277351ade65c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:59.398258Z","signature_b64":"Qv8ybVwXLPemc/ul15W1H9/RyIudHCHC1o3puATEjZ7z0Zw+yyo1EQeUrAfS2WTFvKfHL4az4YZGsS5PAlEqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f634e652ec7504d5a41b2982e240c2ee31c8e5ba624d0cdb424d09720eb9c5f","last_reissued_at":"2026-07-05T08:04:59.397774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:59.397774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Bo Li, Mikkel N. Schmidt, Sebastian U. Stich, Tommy S. Alstr{\\o}m, Yasin Esfandiari","submitted_at":"2023-06-23T02:19:52Z","abstract_excerpt":"In federated learning, data heterogeneity is a critical challenge. A straightforward solution is to shuffle the clients' data to homogenize the distribution. However, this may violate data access rights, and how and when shuffling can accelerate the convergence of a federated optimization algorithm is not theoretically well understood. In this paper, we establish a precise and quantifiable correspondence between data heterogeneity and parameters in the convergence rate when a fraction of data is shuffled across clients. We prove that shuffling can quadratically reduce the gradient dissimilarit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13263","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/2306.13263/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":"2306.13263","created_at":"2026-07-05T08:04:59.397831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13263v2","created_at":"2026-07-05T08:04:59.397831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13263","created_at":"2026-07-05T08:04:59.397831+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5RU4ZJOY5IE","created_at":"2026-07-05T08:04:59.397831+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5RU4ZJOY5IE2WSB","created_at":"2026-07-05T08:04:59.397831+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5RU4ZJO","created_at":"2026-07-05T08:04:59.397831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18904","citing_title":"FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3","json":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3.json","graph_json":"https://pith.science/api/pith-number/L5RU4ZJOY5IE2WSBWKMC4JAMF3/graph.json","events_json":"https://pith.science/api/pith-number/L5RU4ZJOY5IE2WSBWKMC4JAMF3/events.json","paper":"https://pith.science/paper/L5RU4ZJO"},"agent_actions":{"view_html":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3","download_json":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3.json","view_paper":"https://pith.science/paper/L5RU4ZJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13263&json=true","fetch_graph":"https://pith.science/api/pith-number/L5RU4ZJOY5IE2WSBWKMC4JAMF3/graph.json","fetch_events":"https://pith.science/api/pith-number/L5RU4ZJOY5IE2WSBWKMC4JAMF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3/action/storage_attestation","attest_author":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3/action/author_attestation","sign_citation":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3/action/citation_signature","submit_replication":"https://pith.science/pith/L5RU4ZJOY5IE2WSBWKMC4JAMF3/action/replication_record"}},"created_at":"2026-07-05T08:04:59.397831+00:00","updated_at":"2026-07-05T08:04:59.397831+00:00"}