{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WKSLR2G7GXBWQKN22CVGIPEPNC","short_pith_number":"pith:WKSLR2G7","schema_version":"1.0","canonical_sha256":"b2a4b8e8df35c36829bad0aa643c8f688cd6bc2a3fed08c263e11322ef7dc3cf","source":{"kind":"arxiv","id":"2102.07078","version":3},"attestation_state":"computed","paper":{"title":"Exploiting Shared Representations for Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aryan Mokhtari, Hamed Hassani, Liam Collins, Sanjay Shakkottai","submitted_at":"2021-02-14T05:36:25Z","abstract_excerpt":"Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be fully-realized in federated settings. Although data in federated settings is often non-i.i.d. across clients, the success of centralized deep learning suggests that data often shares a global feature representation, while the statistical heterogeneity across clients or tasks is concentrated in the labels. Based on this intuition, we propose a novel federated"},"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":"2102.07078","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T05:36:25Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"1922bde9be94b72c5644a8d98646b517e789e3eb3c920541b23b10a90af2ac09","abstract_canon_sha256":"e346c307e899aff334760fbb4f74037990b33b3f93ee2fa8aeb9db4a4a867ebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:25.764537Z","signature_b64":"n8rIL+gkk8N3LovO0iJB//k1OWgxomz3a4re7iSXR9PKyd8Fv+IZhqAzIO594x1plIUvoYrdAFIL/L1oBMPHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a4b8e8df35c36829bad0aa643c8f688cd6bc2a3fed08c263e11322ef7dc3cf","last_reissued_at":"2026-07-05T05:54:25.764047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:25.764047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Shared Representations for Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aryan Mokhtari, Hamed Hassani, Liam Collins, Sanjay Shakkottai","submitted_at":"2021-02-14T05:36:25Z","abstract_excerpt":"Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be fully-realized in federated settings. Although data in federated settings is often non-i.i.d. across clients, the success of centralized deep learning suggests that data often shares a global feature representation, while the statistical heterogeneity across clients or tasks is concentrated in the labels. Based on this intuition, we propose a novel federated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07078","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/2102.07078/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":"2102.07078","created_at":"2026-07-05T05:54:25.764108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07078v3","created_at":"2026-07-05T05:54:25.764108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07078","created_at":"2026-07-05T05:54:25.764108+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKSLR2G7GXBW","created_at":"2026-07-05T05:54:25.764108+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKSLR2G7GXBWQKN2","created_at":"2026-07-05T05:54:25.764108+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKSLR2G7","created_at":"2026-07-05T05:54:25.764108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC","json":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC.json","graph_json":"https://pith.science/api/pith-number/WKSLR2G7GXBWQKN22CVGIPEPNC/graph.json","events_json":"https://pith.science/api/pith-number/WKSLR2G7GXBWQKN22CVGIPEPNC/events.json","paper":"https://pith.science/paper/WKSLR2G7"},"agent_actions":{"view_html":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC","download_json":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC.json","view_paper":"https://pith.science/paper/WKSLR2G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07078&json=true","fetch_graph":"https://pith.science/api/pith-number/WKSLR2G7GXBWQKN22CVGIPEPNC/graph.json","fetch_events":"https://pith.science/api/pith-number/WKSLR2G7GXBWQKN22CVGIPEPNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC/action/storage_attestation","attest_author":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC/action/author_attestation","sign_citation":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC/action/citation_signature","submit_replication":"https://pith.science/pith/WKSLR2G7GXBWQKN22CVGIPEPNC/action/replication_record"}},"created_at":"2026-07-05T05:54:25.764108+00:00","updated_at":"2026-07-05T05:54:25.764108+00:00"}