{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HDXWR2BAZOWJGNCKBQBD2QFXQS","short_pith_number":"pith:HDXWR2BA","schema_version":"1.0","canonical_sha256":"38ef68e820cbac93344a0c023d40b7848a693e5298bf1e01dd034b8300106416","source":{"kind":"arxiv","id":"2003.13461","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mehrdad Mahdavi, Mohammad Mahdi Kamani, Yuyang Deng","submitted_at":"2020-03-30T13:19:37Z","abstract_excerpt":"Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this paper, we advocate an adaptive personalized federated learning (APFL) algorithm, where each client will train their local models while contributing to the global model. We derive the generalization bound of mixture of local and global models, and find the optimal mixing parameter. We also propose a communication-efficient optimization method to collaboratively learn the personaliz"},"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":"2003.13461","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T13:19:37Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"d046035f139d607eff8c4f54f8e03b84b77bf744a07b083069e3271cc1830b66","abstract_canon_sha256":"97efb034dbc81ddf1cf66a31834e665db291fffb2d3b2d786f6f2eb06158daed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:36.364463Z","signature_b64":"24+YOWlpWvhj7CliTeV0XDYI1/r5R5JWB9uEptdk4aRiPuRDlHdDGCAlYvhkKcVKpGclqGFMqLJcTjIuM1hGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ef68e820cbac93344a0c023d40b7848a693e5298bf1e01dd034b8300106416","last_reissued_at":"2026-07-05T01:49:36.363998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:36.363998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mehrdad Mahdavi, Mohammad Mahdi Kamani, Yuyang Deng","submitted_at":"2020-03-30T13:19:37Z","abstract_excerpt":"Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this paper, we advocate an adaptive personalized federated learning (APFL) algorithm, where each client will train their local models while contributing to the global model. We derive the generalization bound of mixture of local and global models, and find the optimal mixing parameter. We also propose a communication-efficient optimization method to collaboratively learn the personaliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13461","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/2003.13461/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":"2003.13461","created_at":"2026-07-05T01:49:36.364055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.13461v3","created_at":"2026-07-05T01:49:36.364055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13461","created_at":"2026-07-05T01:49:36.364055+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDXWR2BAZOWJ","created_at":"2026-07-05T01:49:36.364055+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDXWR2BAZOWJGNCK","created_at":"2026-07-05T01:49:36.364055+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDXWR2BA","created_at":"2026-07-05T01:49:36.364055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13287","citing_title":"Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10916","citing_title":"Range Penalization: Theoretical Insights with Applications in Federated Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02172","citing_title":"Closing the Alignment-Maturity Gap in Federated Prototype Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11165","citing_title":"COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26571","citing_title":"Separate Aggregation of Split Network for Personalized Federated Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22898","citing_title":"FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2409.03897","citing_title":"On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22897","citing_title":"Federated Multi-Task Clustering","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14423","citing_title":"Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02616","citing_title":"Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11815","citing_title":"Fed-BAC: Federated Bandit-Guided Additive Clustering in Hierarchical Federated Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11165","citing_title":"COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23386","citing_title":"A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02247","citing_title":"Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10678","citing_title":"FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16574","citing_title":"FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS","json":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS.json","graph_json":"https://pith.science/api/pith-number/HDXWR2BAZOWJGNCKBQBD2QFXQS/graph.json","events_json":"https://pith.science/api/pith-number/HDXWR2BAZOWJGNCKBQBD2QFXQS/events.json","paper":"https://pith.science/paper/HDXWR2BA"},"agent_actions":{"view_html":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS","download_json":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS.json","view_paper":"https://pith.science/paper/HDXWR2BA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.13461&json=true","fetch_graph":"https://pith.science/api/pith-number/HDXWR2BAZOWJGNCKBQBD2QFXQS/graph.json","fetch_events":"https://pith.science/api/pith-number/HDXWR2BAZOWJGNCKBQBD2QFXQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS/action/storage_attestation","attest_author":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS/action/author_attestation","sign_citation":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS/action/citation_signature","submit_replication":"https://pith.science/pith/HDXWR2BAZOWJGNCKBQBD2QFXQS/action/replication_record"}},"created_at":"2026-07-05T01:49:36.364055+00:00","updated_at":"2026-07-05T01:49:36.364055+00:00"}