{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ODH2FXCDPQDXNRDD4POEXEUC3F","short_pith_number":"pith:ODH2FXCD","schema_version":"1.0","canonical_sha256":"70cfa2dc437c0776c463e3dc4b9282d97398d0fd21db54a663953e6bef013a82","source":{"kind":"arxiv","id":"2502.07456","version":2},"attestation_state":"computed","paper":{"title":"FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aoxiang Sun, Jingcai Guo, Siyi Pan, Yuxia Sun, Zhixiao Fu","submitted_at":"2025-02-11T11:00:58Z","abstract_excerpt":"Personalized federated learning (PFL) tailors models to clients' unique data distributions while preserving privacy. However, existing aggregation-weight-based PFL methods often struggle with heterogeneous data, facing challenges in accuracy, computational efficiency, and communication overhead. We propose FedAPA, a novel PFL method featuring a server-side, gradient-based adaptive aggregation strategy to generate personalized models, by updating aggregation weights based on gradients of client-parameter changes with respect to the aggregation weights in a centralized manner. FedAPA guarantees "},"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":"2502.07456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T11:00:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"365fd6684ca87dddec939c2edfe959881071f39cd0514c47c9d97e001e0813be","abstract_canon_sha256":"ff2896ecb7cafb31f5e007022aeb894b1e0d7e88e888e2b0eff68572cb1da783"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:51.057474Z","signature_b64":"yNpLa8Z6Tm7c5qrtzD5k1+ZFHRUfuZYBMYths6zBJpJiJsbDLxAqPsgIWFeaUW85hpH4HebQjf9xe7P4hKwwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cfa2dc437c0776c463e3dc4b9282d97398d0fd21db54a663953e6bef013a82","last_reissued_at":"2026-07-05T10:14:51.056954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:51.056954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aoxiang Sun, Jingcai Guo, Siyi Pan, Yuxia Sun, Zhixiao Fu","submitted_at":"2025-02-11T11:00:58Z","abstract_excerpt":"Personalized federated learning (PFL) tailors models to clients' unique data distributions while preserving privacy. However, existing aggregation-weight-based PFL methods often struggle with heterogeneous data, facing challenges in accuracy, computational efficiency, and communication overhead. We propose FedAPA, a novel PFL method featuring a server-side, gradient-based adaptive aggregation strategy to generate personalized models, by updating aggregation weights based on gradients of client-parameter changes with respect to the aggregation weights in a centralized manner. FedAPA guarantees "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07456","kind":"arxiv","version":2},"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/2502.07456/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":"2502.07456","created_at":"2026-07-05T10:14:51.057017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07456v2","created_at":"2026-07-05T10:14:51.057017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07456","created_at":"2026-07-05T10:14:51.057017+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODH2FXCDPQDX","created_at":"2026-07-05T10:14:51.057017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODH2FXCDPQDXNRDD","created_at":"2026-07-05T10:14:51.057017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODH2FXCD","created_at":"2026-07-05T10:14:51.057017+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/ODH2FXCDPQDXNRDD4POEXEUC3F","json":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F.json","graph_json":"https://pith.science/api/pith-number/ODH2FXCDPQDXNRDD4POEXEUC3F/graph.json","events_json":"https://pith.science/api/pith-number/ODH2FXCDPQDXNRDD4POEXEUC3F/events.json","paper":"https://pith.science/paper/ODH2FXCD"},"agent_actions":{"view_html":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F","download_json":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F.json","view_paper":"https://pith.science/paper/ODH2FXCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07456&json=true","fetch_graph":"https://pith.science/api/pith-number/ODH2FXCDPQDXNRDD4POEXEUC3F/graph.json","fetch_events":"https://pith.science/api/pith-number/ODH2FXCDPQDXNRDD4POEXEUC3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F/action/storage_attestation","attest_author":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F/action/author_attestation","sign_citation":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F/action/citation_signature","submit_replication":"https://pith.science/pith/ODH2FXCDPQDXNRDD4POEXEUC3F/action/replication_record"}},"created_at":"2026-07-05T10:14:51.057017+00:00","updated_at":"2026-07-05T10:14:51.057017+00:00"}