{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HRIDKSBDEQ2PZQJNPLHKD3P7FE","short_pith_number":"pith:HRIDKSBD","schema_version":"1.0","canonical_sha256":"3c503548232434fcc12d7acea1edff290de19d7e7503b4d7665337cba665db07","source":{"kind":"arxiv","id":"2306.14245","version":1},"attestation_state":"computed","paper":{"title":"FedSampling: A Better Sampling Strategy for Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangzhao Wu, Lingjuan Lyu, Tao Qi, Xing Xie, Yongfeng Huang","submitted_at":"2023-06-25T13:38:51Z","abstract_excerpt":"Federated learning (FL) is an important technique for learning models from decentralized data in a privacy-preserving way. Existing FL methods usually uniformly sample clients for local model learning in each round. However, different clients may have significantly different data sizes, and the clients with more data cannot have more opportunities to contribute to model training, which may lead to inferior performance. In this paper, instead of client uniform sampling, we propose a novel data uniform sampling strategy for federated learning (FedSampling), which can effectively improve the perf"},"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":"2306.14245","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T13:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"44b8ab9f5ba6f9d77cbb5be6598d944cedbf5936d90a278e4e407b15a9a24917","abstract_canon_sha256":"4feff4990843f26f5f6d459703a980fef1c3d892372cd23e41d25cd8aa704a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:33.900176Z","signature_b64":"h+6cNjeF4EzI1EhjwbBfqrTUJKI8RqAlVYUkTYlSe4AYNgzS4rQiHg3yTFObPXKKMKeEDQzOdagKqF2IeOT8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c503548232434fcc12d7acea1edff290de19d7e7503b4d7665337cba665db07","last_reissued_at":"2026-07-05T06:24:33.899773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:33.899773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSampling: A Better Sampling Strategy for Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangzhao Wu, Lingjuan Lyu, Tao Qi, Xing Xie, Yongfeng Huang","submitted_at":"2023-06-25T13:38:51Z","abstract_excerpt":"Federated learning (FL) is an important technique for learning models from decentralized data in a privacy-preserving way. Existing FL methods usually uniformly sample clients for local model learning in each round. However, different clients may have significantly different data sizes, and the clients with more data cannot have more opportunities to contribute to model training, which may lead to inferior performance. In this paper, instead of client uniform sampling, we propose a novel data uniform sampling strategy for federated learning (FedSampling), which can effectively improve the perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14245","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/2306.14245/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":"2306.14245","created_at":"2026-07-05T06:24:33.899831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14245v1","created_at":"2026-07-05T06:24:33.899831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14245","created_at":"2026-07-05T06:24:33.899831+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRIDKSBDEQ2P","created_at":"2026-07-05T06:24:33.899831+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRIDKSBDEQ2PZQJN","created_at":"2026-07-05T06:24:33.899831+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRIDKSBD","created_at":"2026-07-05T06:24:33.899831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14226","citing_title":"FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE","json":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE.json","graph_json":"https://pith.science/api/pith-number/HRIDKSBDEQ2PZQJNPLHKD3P7FE/graph.json","events_json":"https://pith.science/api/pith-number/HRIDKSBDEQ2PZQJNPLHKD3P7FE/events.json","paper":"https://pith.science/paper/HRIDKSBD"},"agent_actions":{"view_html":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE","download_json":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE.json","view_paper":"https://pith.science/paper/HRIDKSBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14245&json=true","fetch_graph":"https://pith.science/api/pith-number/HRIDKSBDEQ2PZQJNPLHKD3P7FE/graph.json","fetch_events":"https://pith.science/api/pith-number/HRIDKSBDEQ2PZQJNPLHKD3P7FE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE/action/storage_attestation","attest_author":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE/action/author_attestation","sign_citation":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE/action/citation_signature","submit_replication":"https://pith.science/pith/HRIDKSBDEQ2PZQJNPLHKD3P7FE/action/replication_record"}},"created_at":"2026-07-05T06:24:33.899831+00:00","updated_at":"2026-07-05T06:24:33.899831+00:00"}