{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WSQGQYDOS7SI5QZQ6TEQACXFCB","short_pith_number":"pith:WSQGQYDO","schema_version":"1.0","canonical_sha256":"b4a068606e97e48ec330f4c9000ae51071b5b4b02b4827cc774a943a83dd194d","source":{"kind":"arxiv","id":"2303.10254","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Model Personalization for Federated Supervised SVM in Heterogeneous Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksei Ponomarenko-Timofeev, Nageen Himayat, Olga Galinina, Ravikumar Balakrishnan, Sergey Andreev, Yevgeni Koucheryavy","submitted_at":"2023-03-17T21:36:01Z","abstract_excerpt":"Federated systems enable collaborative training on highly heterogeneous data through model personalization, which can be facilitated by employing multi-task learning algorithms. However, significant variation in device computing capabilities may result in substantial degradation in the convergence rate of training. To accelerate the learning procedure for diverse participants in a multi-task federated setting, more efficient and robust methods need to be developed. In this paper, we design an efficient iterative distributed method based on the alternating direction method of multipliers (ADMM)"},"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":"2303.10254","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T21:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"975e1e33a26b4aae22199f40a4960fc0781ffaa311c079a05cec2e73760e3781","abstract_canon_sha256":"0d110f38cc386a89ec1328bccf5f8eba80b389d97f1fa6435859b32d08f917c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:56.465865Z","signature_b64":"wkcwo5LYd6AoVcPqzfxNXL65JN9lSHs2IYTlHD3xLKjcEIRfQbl7Ym3bTNolb9oVCcEMcjh6pczC2HvoKJJ7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a068606e97e48ec330f4c9000ae51071b5b4b02b4827cc774a943a83dd194d","last_reissued_at":"2026-07-05T05:56:56.465421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:56.465421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Model Personalization for Federated Supervised SVM in Heterogeneous Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksei Ponomarenko-Timofeev, Nageen Himayat, Olga Galinina, Ravikumar Balakrishnan, Sergey Andreev, Yevgeni Koucheryavy","submitted_at":"2023-03-17T21:36:01Z","abstract_excerpt":"Federated systems enable collaborative training on highly heterogeneous data through model personalization, which can be facilitated by employing multi-task learning algorithms. However, significant variation in device computing capabilities may result in substantial degradation in the convergence rate of training. To accelerate the learning procedure for diverse participants in a multi-task federated setting, more efficient and robust methods need to be developed. In this paper, we design an efficient iterative distributed method based on the alternating direction method of multipliers (ADMM)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10254","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/2303.10254/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":"2303.10254","created_at":"2026-07-05T05:56:56.465477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10254v2","created_at":"2026-07-05T05:56:56.465477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10254","created_at":"2026-07-05T05:56:56.465477+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSQGQYDOS7SI","created_at":"2026-07-05T05:56:56.465477+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSQGQYDOS7SI5QZQ","created_at":"2026-07-05T05:56:56.465477+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSQGQYDO","created_at":"2026-07-05T05:56:56.465477+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/WSQGQYDOS7SI5QZQ6TEQACXFCB","json":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB.json","graph_json":"https://pith.science/api/pith-number/WSQGQYDOS7SI5QZQ6TEQACXFCB/graph.json","events_json":"https://pith.science/api/pith-number/WSQGQYDOS7SI5QZQ6TEQACXFCB/events.json","paper":"https://pith.science/paper/WSQGQYDO"},"agent_actions":{"view_html":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB","download_json":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB.json","view_paper":"https://pith.science/paper/WSQGQYDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10254&json=true","fetch_graph":"https://pith.science/api/pith-number/WSQGQYDOS7SI5QZQ6TEQACXFCB/graph.json","fetch_events":"https://pith.science/api/pith-number/WSQGQYDOS7SI5QZQ6TEQACXFCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB/action/storage_attestation","attest_author":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB/action/author_attestation","sign_citation":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB/action/citation_signature","submit_replication":"https://pith.science/pith/WSQGQYDOS7SI5QZQ6TEQACXFCB/action/replication_record"}},"created_at":"2026-07-05T05:56:56.465477+00:00","updated_at":"2026-07-05T05:56:56.465477+00:00"}