{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PEHUSVJNAVUTUO6O7NK4OB4TQT","short_pith_number":"pith:PEHUSVJN","schema_version":"1.0","canonical_sha256":"790f49552d05693a3bcefb55c7079384c9a3b1cc2cebd61af5c01e2824cff367","source":{"kind":"arxiv","id":"2412.00334","version":2},"attestation_state":"computed","paper":{"title":"EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun Li, Cui Miao, Jie Zhou, Meihan Wu, Ming Li, Tao Chang, Xiangyu Xu, Xiaodong Wang","submitted_at":"2024-11-30T03:20:14Z","abstract_excerpt":"Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive biases inherent in CNNs. However, efficient federated training of ViTs on resource-constrained edge devices remains unexplored in the community. In this paper, we propose EFTViT, a hierarchical federated framework that leverages masked images to enable efficient, full-parameter training on resource-constrained edge devices, offering substantial benefits for le"},"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":"2412.00334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-30T03:20:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f6399cc994f0ecb97b58666c2889ed9dcf609d47c0be154200e1454dfeb3671","abstract_canon_sha256":"082600cd686d45e7c72c36b509b6598454d160d5fb41f8d8e7936bad2591e7e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:56.055885Z","signature_b64":"OFTabWe5OpmSjWJy/KrPmTdmkX/Du2gNRs2y1h6uqdMj3GTfLzCmXfkNsf8//q2f4nwTpfZWBPIb/SXfW6xAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"790f49552d05693a3bcefb55c7079384c9a3b1cc2cebd61af5c01e2824cff367","last_reissued_at":"2026-07-05T12:01:56.055364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:56.055364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun Li, Cui Miao, Jie Zhou, Meihan Wu, Ming Li, Tao Chang, Xiangyu Xu, Xiaodong Wang","submitted_at":"2024-11-30T03:20:14Z","abstract_excerpt":"Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive biases inherent in CNNs. However, efficient federated training of ViTs on resource-constrained edge devices remains unexplored in the community. In this paper, we propose EFTViT, a hierarchical federated framework that leverages masked images to enable efficient, full-parameter training on resource-constrained edge devices, offering substantial benefits for le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00334","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/2412.00334/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":"2412.00334","created_at":"2026-07-05T12:01:56.055422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00334v2","created_at":"2026-07-05T12:01:56.055422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00334","created_at":"2026-07-05T12:01:56.055422+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEHUSVJNAVUT","created_at":"2026-07-05T12:01:56.055422+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEHUSVJNAVUTUO6O","created_at":"2026-07-05T12:01:56.055422+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEHUSVJN","created_at":"2026-07-05T12:01:56.055422+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/PEHUSVJNAVUTUO6O7NK4OB4TQT","json":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT.json","graph_json":"https://pith.science/api/pith-number/PEHUSVJNAVUTUO6O7NK4OB4TQT/graph.json","events_json":"https://pith.science/api/pith-number/PEHUSVJNAVUTUO6O7NK4OB4TQT/events.json","paper":"https://pith.science/paper/PEHUSVJN"},"agent_actions":{"view_html":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT","download_json":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT.json","view_paper":"https://pith.science/paper/PEHUSVJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00334&json=true","fetch_graph":"https://pith.science/api/pith-number/PEHUSVJNAVUTUO6O7NK4OB4TQT/graph.json","fetch_events":"https://pith.science/api/pith-number/PEHUSVJNAVUTUO6O7NK4OB4TQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT/action/storage_attestation","attest_author":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT/action/author_attestation","sign_citation":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT/action/citation_signature","submit_replication":"https://pith.science/pith/PEHUSVJNAVUTUO6O7NK4OB4TQT/action/replication_record"}},"created_at":"2026-07-05T12:01:56.055422+00:00","updated_at":"2026-07-05T12:01:56.055422+00:00"}