{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MEHTTDYDQVW744TOK6RAPKK5SE","short_pith_number":"pith:MEHTTDYD","schema_version":"1.0","canonical_sha256":"610f398f03856dfe726e57a207a95d912b5a4ee196466ee1d4f036ba9de0d635","source":{"kind":"arxiv","id":"2312.09006","version":3},"attestation_state":"computed","paper":{"title":"FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gang Wang, Han Yu, Liping Yi, Lizhen Cui, Xiaoguang Liu, Xiaoxiao Li, Zhuan Shi","submitted_at":"2023-12-14T14:55:32Z","abstract_excerpt":"Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system heterogeneity. Model-Heterogeneous Personalized FL (MHPFL) has emerged to address this challenge. Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs. To address these limitations, we propose the Federated Semantic Similarity Aggregation (FedSSA)"},"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":"2312.09006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T14:55:32Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"9ba9382ce27c636a446679560ef1f47012fe2675b15834f3cece9f0b76aa3bfc","abstract_canon_sha256":"468ff17e005e1c03b3bb40a3d561a8212a66533c4f18b7f1d25304242da2e6ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:46.902929Z","signature_b64":"PBkf/F9XqKhj+GnCdBx3x2QTZQbfuwiEU1dRO/fnE1o8rOZXe9vDjUKgJiJjSOj7IFwPhdqvL64aA6AWmg7lAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610f398f03856dfe726e57a207a95d912b5a4ee196466ee1d4f036ba9de0d635","last_reissued_at":"2026-07-05T08:09:46.902141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:46.902141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gang Wang, Han Yu, Liping Yi, Lizhen Cui, Xiaoguang Liu, Xiaoxiao Li, Zhuan Shi","submitted_at":"2023-12-14T14:55:32Z","abstract_excerpt":"Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system heterogeneity. Model-Heterogeneous Personalized FL (MHPFL) has emerged to address this challenge. Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs. To address these limitations, we propose the Federated Semantic Similarity Aggregation (FedSSA)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09006","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/2312.09006/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":"2312.09006","created_at":"2026-07-05T08:09:46.902349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09006v3","created_at":"2026-07-05T08:09:46.902349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09006","created_at":"2026-07-05T08:09:46.902349+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEHTTDYDQVW7","created_at":"2026-07-05T08:09:46.902349+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEHTTDYDQVW744TO","created_at":"2026-07-05T08:09:46.902349+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEHTTDYD","created_at":"2026-07-05T08:09:46.902349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06031","citing_title":"Efficient Federated Learning with Timely Update Dissemination","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE","json":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE.json","graph_json":"https://pith.science/api/pith-number/MEHTTDYDQVW744TOK6RAPKK5SE/graph.json","events_json":"https://pith.science/api/pith-number/MEHTTDYDQVW744TOK6RAPKK5SE/events.json","paper":"https://pith.science/paper/MEHTTDYD"},"agent_actions":{"view_html":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE","download_json":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE.json","view_paper":"https://pith.science/paper/MEHTTDYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09006&json=true","fetch_graph":"https://pith.science/api/pith-number/MEHTTDYDQVW744TOK6RAPKK5SE/graph.json","fetch_events":"https://pith.science/api/pith-number/MEHTTDYDQVW744TOK6RAPKK5SE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE/action/storage_attestation","attest_author":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE/action/author_attestation","sign_citation":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE/action/citation_signature","submit_replication":"https://pith.science/pith/MEHTTDYDQVW744TOK6RAPKK5SE/action/replication_record"}},"created_at":"2026-07-05T08:09:46.902349+00:00","updated_at":"2026-07-05T08:09:46.902349+00:00"}