{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ERXFBURC6BKGEZAYUDGTRN7OLJ","short_pith_number":"pith:ERXFBURC","schema_version":"1.0","canonical_sha256":"246e50d222f054626418a0cd38b7ee5a5176dd42712d232799a42091552b4642","source":{"kind":"arxiv","id":"2006.09637","version":3},"attestation_state":"computed","paper":{"title":"FedCD: Improving Performance in non-IID Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Lin, Jessica Zhao, Kavya Kopparapu","submitted_at":"2020-06-17T03:45:25Z","abstract_excerpt":"Federated learning has been widely applied to enable decentralized devices, which each have their own local data, to learn a shared model. However, learning from real-world data can be challenging, as it is rarely identically and independently distributed (IID) across edge devices (a key assumption for current high-performing and low-bandwidth algorithms). We present a novel approach, FedCD, which clones and deletes models to dynamically group devices with similar data. Experiments on the CIFAR-10 dataset show that FedCD achieves higher accuracy and faster convergence compared to a FedAvg base"},"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":"2006.09637","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:45:25Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"7364d8bb0d7dcd5ec3e6890b0bed225cf7cdce777cf6eaa5796f5f4086a1365b","abstract_canon_sha256":"ebaa4dba8cd1fbbbc6e3189399c451dd809b98a074c1320d728f0ed8fb49e381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:19.443269Z","signature_b64":"2UpR4sNZO8/sfvCXHiiYnKwcck1z8+/XgDLziRznqeLK4HbXLjc7Jhx240O791xgyTD+8LXVsqLTHLEEBs8ACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"246e50d222f054626418a0cd38b7ee5a5176dd42712d232799a42091552b4642","last_reissued_at":"2026-07-05T01:22:19.442843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:19.442843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedCD: Improving Performance in non-IID Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Lin, Jessica Zhao, Kavya Kopparapu","submitted_at":"2020-06-17T03:45:25Z","abstract_excerpt":"Federated learning has been widely applied to enable decentralized devices, which each have their own local data, to learn a shared model. However, learning from real-world data can be challenging, as it is rarely identically and independently distributed (IID) across edge devices (a key assumption for current high-performing and low-bandwidth algorithms). We present a novel approach, FedCD, which clones and deletes models to dynamically group devices with similar data. Experiments on the CIFAR-10 dataset show that FedCD achieves higher accuracy and faster convergence compared to a FedAvg base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09637","kind":"arxiv","version":3},"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/2006.09637/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":"2006.09637","created_at":"2026-07-05T01:22:19.442905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09637v3","created_at":"2026-07-05T01:22:19.442905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09637","created_at":"2026-07-05T01:22:19.442905+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERXFBURC6BKG","created_at":"2026-07-05T01:22:19.442905+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERXFBURC6BKGEZAY","created_at":"2026-07-05T01:22:19.442905+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERXFBURC","created_at":"2026-07-05T01:22:19.442905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08219","citing_title":"Benchmark Evaluation of Federated Learning on Multi-organ Images","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ","json":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ.json","graph_json":"https://pith.science/api/pith-number/ERXFBURC6BKGEZAYUDGTRN7OLJ/graph.json","events_json":"https://pith.science/api/pith-number/ERXFBURC6BKGEZAYUDGTRN7OLJ/events.json","paper":"https://pith.science/paper/ERXFBURC"},"agent_actions":{"view_html":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ","download_json":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ.json","view_paper":"https://pith.science/paper/ERXFBURC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09637&json=true","fetch_graph":"https://pith.science/api/pith-number/ERXFBURC6BKGEZAYUDGTRN7OLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ERXFBURC6BKGEZAYUDGTRN7OLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ/action/storage_attestation","attest_author":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ/action/author_attestation","sign_citation":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ/action/citation_signature","submit_replication":"https://pith.science/pith/ERXFBURC6BKGEZAYUDGTRN7OLJ/action/replication_record"}},"created_at":"2026-07-05T01:22:19.442905+00:00","updated_at":"2026-07-05T01:22:19.442905+00:00"}