{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WQUBE4HT5S6YAROQTANUFQLSDK","short_pith_number":"pith:WQUBE4HT","schema_version":"1.0","canonical_sha256":"b4281270f3ecbd8045d0981b42c1721a993a0499bdfa004219d81507fe5af90c","source":{"kind":"arxiv","id":"2301.12755","version":2},"attestation_state":"computed","paper":{"title":"Efficient Node Selection in Private Personalized Decentralized Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gillblad, Edvin Listo Zec, Johan \\\"Ostman, Olof Mogren","submitted_at":"2023-01-30T10:01:18Z","abstract_excerpt":"Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node "},"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":"2301.12755","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T10:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"1d2d24da2753f1b98882c5b915b572d1319c5c8639a6c29d69f6ddfa0d396127","abstract_canon_sha256":"d7f381503f84e6bcdedfa367e9200da4fe66dd0e5b164b6d8a38316089f3fb13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:48.934151Z","signature_b64":"Jh5/W3aupN5mxCsBFK8v9jprjdJo9uCMqpu/o0sSUEQrHnBkBj1BeUKu+XPlGU2yVy1nRLf7A/GS3m3VSm/PCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4281270f3ecbd8045d0981b42c1721a993a0499bdfa004219d81507fe5af90c","last_reissued_at":"2026-07-05T07:33:48.933714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:48.933714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Node Selection in Private Personalized Decentralized Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gillblad, Edvin Listo Zec, Johan \\\"Ostman, Olof Mogren","submitted_at":"2023-01-30T10:01:18Z","abstract_excerpt":"Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12755","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/2301.12755/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":"2301.12755","created_at":"2026-07-05T07:33:48.933770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12755v2","created_at":"2026-07-05T07:33:48.933770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12755","created_at":"2026-07-05T07:33:48.933770+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQUBE4HT5S6Y","created_at":"2026-07-05T07:33:48.933770+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQUBE4HT5S6YAROQ","created_at":"2026-07-05T07:33:48.933770+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQUBE4HT","created_at":"2026-07-05T07:33:48.933770+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/WQUBE4HT5S6YAROQTANUFQLSDK","json":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK.json","graph_json":"https://pith.science/api/pith-number/WQUBE4HT5S6YAROQTANUFQLSDK/graph.json","events_json":"https://pith.science/api/pith-number/WQUBE4HT5S6YAROQTANUFQLSDK/events.json","paper":"https://pith.science/paper/WQUBE4HT"},"agent_actions":{"view_html":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK","download_json":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK.json","view_paper":"https://pith.science/paper/WQUBE4HT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12755&json=true","fetch_graph":"https://pith.science/api/pith-number/WQUBE4HT5S6YAROQTANUFQLSDK/graph.json","fetch_events":"https://pith.science/api/pith-number/WQUBE4HT5S6YAROQTANUFQLSDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK/action/storage_attestation","attest_author":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK/action/author_attestation","sign_citation":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK/action/citation_signature","submit_replication":"https://pith.science/pith/WQUBE4HT5S6YAROQTANUFQLSDK/action/replication_record"}},"created_at":"2026-07-05T07:33:48.933770+00:00","updated_at":"2026-07-05T07:33:48.933770+00:00"}