{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JC6IYE4DGRH5EMDF2BIERXPYPS","short_pith_number":"pith:JC6IYE4D","schema_version":"1.0","canonical_sha256":"48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f","source":{"kind":"arxiv","id":"1912.00818","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning with Personalization Layers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaditya Kumar Singh, Manoj Ghuhan Arivazhagan, Sunav Choudhary, Vinay Aggarwal","submitted_at":"2019-12-02T14:29:00Z","abstract_excerpt":"The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machine learning and necessitates the design of algorithms robust to various sources of heterogeneity. Specifically, statistical heterogeneity of data across user devices can severely degrade the performance of standard federated averaging for traditional machine learning applications like personalization with deep learning. This paper pro-posesFedPer, "},"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":true},"canonical_record":{"source":{"id":"1912.00818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T14:29:00Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"aaff00967d94412e74e8775461e4dd1f418194cb3260248c9afd35e76343df94","abstract_canon_sha256":"2aeb3a4804dda085f6efdf618d4e061bc3d1137aac260836dc6e5601ada5daa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:38:44.382167Z","signature_b64":"z5fe/Xts9h6kQ6XJoGx9RAASpJGBgcWgt8TjwY/krQPGNlRhRqPqg5At1zSJHdYeCp+axHd27i/gChXVKFwBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f","last_reissued_at":"2026-05-18T03:38:44.381648Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:38:44.381648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Personalization Layers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaditya Kumar Singh, Manoj Ghuhan Arivazhagan, Sunav Choudhary, Vinay Aggarwal","submitted_at":"2019-12-02T14:29:00Z","abstract_excerpt":"The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machine learning and necessitates the design of algorithms robust to various sources of heterogeneity. Specifically, statistical heterogeneity of data across user devices can severely degrade the performance of standard federated averaging for traditional machine learning applications like personalization with deep learning. This paper pro-posesFedPer, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"FedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, can combat the ill-effects of statistical heterogeneity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That splitting the network into shared base layers and local personalization layers is sufficient to overcome statistical heterogeneity without needing additional regularization or adaptation mechanisms.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FedPer uses shared base layers and per-user personalization layers to enable effective federated training of deep networks despite non-identical data distributions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"61ac1e2e4a09c5ee3b39ca5bd13a17300c8725c826d6a94ac6e7860ff1a6b2c5"},"source":{"id":"1912.00818","kind":"arxiv","version":1},"verdict":{"id":"b16644ba-a58c-4ccd-9adc-78567b50fd2f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T23:36:31.962727Z","strongest_claim":"FedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, can combat the ill-effects of statistical heterogeneity.","one_line_summary":"FedPer uses shared base layers and per-user personalization layers to enable effective federated training of deep networks despite non-identical data distributions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That splitting the network into shared base layers and local personalization layers is sufficient to overcome statistical heterogeneity without needing additional regularization or adaptation mechanisms.","pith_extraction_headline":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d3ff59f67d7f74a9a0cbb7607b0f4d968a2c83a4304a5167985600e493440150"},"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":"1912.00818","created_at":"2026-05-18T03:38:44.381728+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00818v1","created_at":"2026-05-18T03:38:44.381728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00818","created_at":"2026-05-18T03:38:44.381728+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC6IYE4DGRH5","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC6IYE4DGRH5EMDF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC6IYE4D","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13767","citing_title":"Inpatient Overflow Management with Proximal Policy Optimization","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2501.04066","citing_title":"Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21264","citing_title":"FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02616","citing_title":"Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11010","citing_title":"A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":137,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11433","citing_title":"FedMM: Federated Collaborative Signal Quantization for Multi-Market CTR Prediction","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22885","citing_title":"Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06446","citing_title":"FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06260","citing_title":"Beyond Rigid Alignment: Graph Federated Learning via Dual Manifold Calibration","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03199","citing_title":"PERFECT: Personalized Federated Learning for CBRS Radar Detection","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02247","citing_title":"Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00698","citing_title":"FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00322","citing_title":"Federated Weather Modeling on Sensor Data","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00892","citing_title":"When To Adapt? Adapting the Model or Data in Federated Medical Imaging","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10678","citing_title":"FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11278","citing_title":"Representation-Aligned Multi-Scale Personalization for Federated Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09123","citing_title":"Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07860","citing_title":"On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04611","citing_title":"Dynamic Free-Rider Detection in Federated Learning via Simulated Attack Patterns","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13396","citing_title":"HierFedCEA: Hierarchical Federated Edge Learning for Privacy-Preserving Climate Control Optimization Across Heterogeneous Controlled Environment Agriculture Facilities","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16574","citing_title":"FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04108","citing_title":"MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS","json":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS.json","graph_json":"https://pith.science/api/pith-number/JC6IYE4DGRH5EMDF2BIERXPYPS/graph.json","events_json":"https://pith.science/api/pith-number/JC6IYE4DGRH5EMDF2BIERXPYPS/events.json","paper":"https://pith.science/paper/JC6IYE4D"},"agent_actions":{"view_html":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS","download_json":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS.json","view_paper":"https://pith.science/paper/JC6IYE4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00818&json=true","fetch_graph":"https://pith.science/api/pith-number/JC6IYE4DGRH5EMDF2BIERXPYPS/graph.json","fetch_events":"https://pith.science/api/pith-number/JC6IYE4DGRH5EMDF2BIERXPYPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS/action/storage_attestation","attest_author":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS/action/author_attestation","sign_citation":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS/action/citation_signature","submit_replication":"https://pith.science/pith/JC6IYE4DGRH5EMDF2BIERXPYPS/action/replication_record"}},"created_at":"2026-05-18T03:38:44.381728+00:00","updated_at":"2026-05-18T03:38:44.381728+00:00"}