{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NEAOTWOH3CV4LVG6IFDI5VW7CK","short_pith_number":"pith:NEAOTWOH","schema_version":"1.0","canonical_sha256":"6900e9d9c7d8abc5d4de41468ed6df12859df99c7d5aa520e8c78a89165d1069","source":{"kind":"arxiv","id":"2212.01548","version":2},"attestation_state":"computed","paper":{"title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Luyang Liu, Ming Yan, Mi Zhang, Samiul Alam","submitted_at":"2022-12-03T06:04:11Z","abstract_excerpt":"Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical. However, such constraint not only excludes low-end clients who would otherwise make unique contributions to model training but also restrains clients from training large models due to on-device resource bottlenecks. In this work, we propose FedRolex, a partial training (PT)-based approach that enables model-heterogeneous FL and can train a global server model larger than the largest client model. At its core, FedRolex employs a rolling su"},"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":"2212.01548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-03T06:04:11Z","cross_cats_sorted":["cs.CR","cs.CV","cs.DC"],"title_canon_sha256":"f6e84555e5075b4e10c0c6bc9c66186a358f13f14da47cbe68c936986e1db947","abstract_canon_sha256":"9edee542d438fd84f136294f6c2b4d0ea7cea63b8ab23b8a2a821885c9333bc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:50.597367Z","signature_b64":"+BXio31/MJZ4TIoVmhk5n2bSuaTECjxxYvC1/+n9pZPoaMRSUYzAp/aazyUS25z38TzTBhEJ32PlDcx/4mklBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6900e9d9c7d8abc5d4de41468ed6df12859df99c7d5aa520e8c78a89165d1069","last_reissued_at":"2026-07-05T05:34:50.596949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:50.596949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Luyang Liu, Ming Yan, Mi Zhang, Samiul Alam","submitted_at":"2022-12-03T06:04:11Z","abstract_excerpt":"Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical. However, such constraint not only excludes low-end clients who would otherwise make unique contributions to model training but also restrains clients from training large models due to on-device resource bottlenecks. In this work, we propose FedRolex, a partial training (PT)-based approach that enables model-heterogeneous FL and can train a global server model larger than the largest client model. At its core, FedRolex employs a rolling su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01548","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/2212.01548/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":"2212.01548","created_at":"2026-07-05T05:34:50.597005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01548v2","created_at":"2026-07-05T05:34:50.597005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01548","created_at":"2026-07-05T05:34:50.597005+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEAOTWOH3CV4","created_at":"2026-07-05T05:34:50.597005+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEAOTWOH3CV4LVG6","created_at":"2026-07-05T05:34:50.597005+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEAOTWOH","created_at":"2026-07-05T05:34:50.597005+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/NEAOTWOH3CV4LVG6IFDI5VW7CK","json":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK.json","graph_json":"https://pith.science/api/pith-number/NEAOTWOH3CV4LVG6IFDI5VW7CK/graph.json","events_json":"https://pith.science/api/pith-number/NEAOTWOH3CV4LVG6IFDI5VW7CK/events.json","paper":"https://pith.science/paper/NEAOTWOH"},"agent_actions":{"view_html":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK","download_json":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK.json","view_paper":"https://pith.science/paper/NEAOTWOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01548&json=true","fetch_graph":"https://pith.science/api/pith-number/NEAOTWOH3CV4LVG6IFDI5VW7CK/graph.json","fetch_events":"https://pith.science/api/pith-number/NEAOTWOH3CV4LVG6IFDI5VW7CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK/action/storage_attestation","attest_author":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK/action/author_attestation","sign_citation":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK/action/citation_signature","submit_replication":"https://pith.science/pith/NEAOTWOH3CV4LVG6IFDI5VW7CK/action/replication_record"}},"created_at":"2026-07-05T05:34:50.597005+00:00","updated_at":"2026-07-05T05:34:50.597005+00:00"}