{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BOS23SST4IVXSFTKKQPXAH2ULG","short_pith_number":"pith:BOS23SST","schema_version":"1.0","canonical_sha256":"0ba5adca53e22b79166a541f701f5459acfb35db71469f7cac286a0bff1bcfb4","source":{"kind":"arxiv","id":"2111.14213","version":3},"attestation_state":"computed","paper":{"title":"Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Matias Mendieta, Minwoo Lee, Pu Wang, Taojiannan Yang, Zhengming Ding","submitted_at":"2021-11-28T19:03:39Z","abstract_excerpt":"Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model. Instead, we consider rethinking solutions to data hetero"},"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":"2111.14213","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T19:03:39Z","cross_cats_sorted":["cs.CV","cs.DC"],"title_canon_sha256":"a54bc2b4be54064c3b7d28990a7b1884e0fa34558d12de67943f569e8c92d5df","abstract_canon_sha256":"fcc0e72109ed01890bef2dbd990062c24ee78dbf673a96959e073e4c1a7061a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:40.141367Z","signature_b64":"vUIvuFOtfELT/OsYVb0Y46paggHJGTc1kNjqmfZKz1qRCzw5sVtjey03I2oxRgEfZwmKWp3gb//BkJqQAG7fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba5adca53e22b79166a541f701f5459acfb35db71469f7cac286a0bff1bcfb4","last_reissued_at":"2026-07-05T04:14:40.141003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:40.141003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Matias Mendieta, Minwoo Lee, Pu Wang, Taojiannan Yang, Zhengming Ding","submitted_at":"2021-11-28T19:03:39Z","abstract_excerpt":"Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model. Instead, we consider rethinking solutions to data hetero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14213","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/2111.14213/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":"2111.14213","created_at":"2026-07-05T04:14:40.141051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14213v3","created_at":"2026-07-05T04:14:40.141051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14213","created_at":"2026-07-05T04:14:40.141051+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOS23SST4IVX","created_at":"2026-07-05T04:14:40.141051+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOS23SST4IVXSFTK","created_at":"2026-07-05T04:14:40.141051+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOS23SST","created_at":"2026-07-05T04:14:40.141051+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/BOS23SST4IVXSFTKKQPXAH2ULG","json":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG.json","graph_json":"https://pith.science/api/pith-number/BOS23SST4IVXSFTKKQPXAH2ULG/graph.json","events_json":"https://pith.science/api/pith-number/BOS23SST4IVXSFTKKQPXAH2ULG/events.json","paper":"https://pith.science/paper/BOS23SST"},"agent_actions":{"view_html":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG","download_json":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG.json","view_paper":"https://pith.science/paper/BOS23SST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14213&json=true","fetch_graph":"https://pith.science/api/pith-number/BOS23SST4IVXSFTKKQPXAH2ULG/graph.json","fetch_events":"https://pith.science/api/pith-number/BOS23SST4IVXSFTKKQPXAH2ULG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG/action/storage_attestation","attest_author":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG/action/author_attestation","sign_citation":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG/action/citation_signature","submit_replication":"https://pith.science/pith/BOS23SST4IVXSFTKKQPXAH2ULG/action/replication_record"}},"created_at":"2026-07-05T04:14:40.141051+00:00","updated_at":"2026-07-05T04:14:40.141051+00:00"}