{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMEH6525HTCMB6IJ7U6WFXSZMD","short_pith_number":"pith:QMEH6525","schema_version":"1.0","canonical_sha256":"83087f775d3cc4c0f909fd3d62de5960dc9effcc59c7afb73781d18ba35f4fd0","source":{"kind":"arxiv","id":"2302.06637","version":3},"attestation_state":"computed","paper":{"title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Bo Li, Chaowei Xiao, Chulin Xie, Daguang Xu, De-An Huang, Wenda Chu","submitted_at":"2023-02-13T19:00:37Z","abstract_excerpt":"Personalized Federated Learning (pFL) has emerged as a promising solution to tackle data heterogeneity across clients in FL. However, existing pFL methods either (1) introduce high communication and computation costs or (2) overfit to local data, which can be limited in scope, and are vulnerable to evolved test samples with natural shifts. In this paper, we propose PerAda, a parameter-efficient pFL framework that reduces communication and computational costs and exhibits superior generalization performance, especially under test-time distribution shifts. PerAda reduces the costs by leveraging "},"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":"2302.06637","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T19:00:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a984bc31beee350ac9cf56907a94eae76743347dbc2b03e5756361a9eec2e51a","abstract_canon_sha256":"5d217c90f6deb70dd70a9aa8e7fda1ff4874313370c234ed1dc79e40470c7dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:05.149050Z","signature_b64":"vtMjb78aQpOy8m52c3bfmVj/jPrp+Y/V8YvE7q1gKwsChDAydsbmsr9pEL0JY1gG/7tnBD/8BH73WpX8/07pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83087f775d3cc4c0f909fd3d62de5960dc9effcc59c7afb73781d18ba35f4fd0","last_reissued_at":"2026-07-05T08:47:05.148549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:05.148549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Bo Li, Chaowei Xiao, Chulin Xie, Daguang Xu, De-An Huang, Wenda Chu","submitted_at":"2023-02-13T19:00:37Z","abstract_excerpt":"Personalized Federated Learning (pFL) has emerged as a promising solution to tackle data heterogeneity across clients in FL. However, existing pFL methods either (1) introduce high communication and computation costs or (2) overfit to local data, which can be limited in scope, and are vulnerable to evolved test samples with natural shifts. In this paper, we propose PerAda, a parameter-efficient pFL framework that reduces communication and computational costs and exhibits superior generalization performance, especially under test-time distribution shifts. PerAda reduces the costs by leveraging "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06637","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/2302.06637/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":"2302.06637","created_at":"2026-07-05T08:47:05.148615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06637v3","created_at":"2026-07-05T08:47:05.148615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06637","created_at":"2026-07-05T08:47:05.148615+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMEH6525HTCM","created_at":"2026-07-05T08:47:05.148615+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMEH6525HTCMB6IJ","created_at":"2026-07-05T08:47:05.148615+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMEH6525","created_at":"2026-07-05T08:47:05.148615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.17976","citing_title":"KoopAGRU: A Koopman-based Anomaly Detection in Time-Series using Gated Recurrent Units","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD","json":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD.json","graph_json":"https://pith.science/api/pith-number/QMEH6525HTCMB6IJ7U6WFXSZMD/graph.json","events_json":"https://pith.science/api/pith-number/QMEH6525HTCMB6IJ7U6WFXSZMD/events.json","paper":"https://pith.science/paper/QMEH6525"},"agent_actions":{"view_html":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD","download_json":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD.json","view_paper":"https://pith.science/paper/QMEH6525","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06637&json=true","fetch_graph":"https://pith.science/api/pith-number/QMEH6525HTCMB6IJ7U6WFXSZMD/graph.json","fetch_events":"https://pith.science/api/pith-number/QMEH6525HTCMB6IJ7U6WFXSZMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD/action/storage_attestation","attest_author":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD/action/author_attestation","sign_citation":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD/action/citation_signature","submit_replication":"https://pith.science/pith/QMEH6525HTCMB6IJ7U6WFXSZMD/action/replication_record"}},"created_at":"2026-07-05T08:47:05.148615+00:00","updated_at":"2026-07-05T08:47:05.148615+00:00"}