{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OCAGA7TGYCC5X2TOBNUGWDFOLN","short_pith_number":"pith:OCAGA7TG","schema_version":"1.0","canonical_sha256":"7080607e66c085dbea6e0b686b0cae5b68b86ae20bc3b65df536784e1eead407","source":{"kind":"arxiv","id":"2206.09979","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artur Back de Luca, Guojun Zhang, Xi Chen, Yaoliang Yu","submitted_at":"2022-06-20T19:47:43Z","abstract_excerpt":"Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models. In this setting, one major obstacle is data heterogeneity, i.e., each client having non-identically and independently distributed (non-IID) data. This is analogous to the context of Domain Generalization (DG), where each client can be treated as a different domain. However, while many approaches in DG tackle data heterogeneity from the algorithmic perspective, recent evidence suggests that data augmentation can induce equal or greater per"},"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":"2206.09979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T19:47:43Z","cross_cats_sorted":[],"title_canon_sha256":"31462533047f6ea23e1d7a3fba91850a5603bfb4c5c91b64858c5e561038cf52","abstract_canon_sha256":"bd80320c40fe922ed67736e002bce22000689fdc29fa1a507809b0cebb20ced2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:41.961990Z","signature_b64":"wQSoczh60qmOVW2o+DDNef7gnu6LUBvEZV72as2yl+2GIxes6UIfQYDJLlITiTbtGddP+BWErnxBLfpccfmeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7080607e66c085dbea6e0b686b0cae5b68b86ae20bc3b65df536784e1eead407","last_reissued_at":"2026-07-05T04:33:41.961604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:41.961604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artur Back de Luca, Guojun Zhang, Xi Chen, Yaoliang Yu","submitted_at":"2022-06-20T19:47:43Z","abstract_excerpt":"Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models. In this setting, one major obstacle is data heterogeneity, i.e., each client having non-identically and independently distributed (non-IID) data. This is analogous to the context of Domain Generalization (DG), where each client can be treated as a different domain. However, while many approaches in DG tackle data heterogeneity from the algorithmic perspective, recent evidence suggests that data augmentation can induce equal or greater per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09979","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/2206.09979/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":"2206.09979","created_at":"2026-07-05T04:33:41.961659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09979v1","created_at":"2026-07-05T04:33:41.961659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09979","created_at":"2026-07-05T04:33:41.961659+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCAGA7TGYCC5","created_at":"2026-07-05T04:33:41.961659+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCAGA7TGYCC5X2TO","created_at":"2026-07-05T04:33:41.961659+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCAGA7TG","created_at":"2026-07-05T04:33:41.961659+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/OCAGA7TGYCC5X2TOBNUGWDFOLN","json":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN.json","graph_json":"https://pith.science/api/pith-number/OCAGA7TGYCC5X2TOBNUGWDFOLN/graph.json","events_json":"https://pith.science/api/pith-number/OCAGA7TGYCC5X2TOBNUGWDFOLN/events.json","paper":"https://pith.science/paper/OCAGA7TG"},"agent_actions":{"view_html":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN","download_json":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN.json","view_paper":"https://pith.science/paper/OCAGA7TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09979&json=true","fetch_graph":"https://pith.science/api/pith-number/OCAGA7TGYCC5X2TOBNUGWDFOLN/graph.json","fetch_events":"https://pith.science/api/pith-number/OCAGA7TGYCC5X2TOBNUGWDFOLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN/action/storage_attestation","attest_author":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN/action/author_attestation","sign_citation":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN/action/citation_signature","submit_replication":"https://pith.science/pith/OCAGA7TGYCC5X2TOBNUGWDFOLN/action/replication_record"}},"created_at":"2026-07-05T04:33:41.961659+00:00","updated_at":"2026-07-05T04:33:41.961659+00:00"}