{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SQMEN63F5SJHWXC4C33Y63P25","short_pith_number":"pith:7SQMEN63","schema_version":"1.0","canonical_sha256":"fca0c237db2f6493dae2e0b7bc7b6fd770667279b2e7bd3d622913ae402da1ee","source":{"kind":"arxiv","id":"2402.01862","version":1},"attestation_state":"computed","paper":{"title":"Parametric Feature Transfer: One-shot Federated Learning with Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Bie, Guojun Zhang, Leo Maxime Brunswic, Mahdi Beitollahi, Sobhan Hemati, Xi Chen, Xu Li","submitted_at":"2024-02-02T19:34:46Z","abstract_excerpt":"In one-shot federated learning (FL), clients collaboratively train a global model in a single round of communication. Existing approaches for one-shot FL enhance communication efficiency at the expense of diminished accuracy. This paper introduces FedPFT (Federated Learning with Parametric Feature Transfer), a methodology that harnesses the transferability of foundation models to enhance both accuracy and communication efficiency in one-shot FL. The approach involves transferring per-client parametric models (specifically, Gaussian mixtures) of features extracted from foundation models. Subseq"},"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":"2402.01862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T19:34:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98272e43de3b24df4123556243890903a61649d32a2cb4b0a3a7652ae06cf996","abstract_canon_sha256":"52428f78dfac5598763b723eefc523184e1a02b1365820837896bb4ac44e3d2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:07.765950Z","signature_b64":"uVwGQ8ifsOdZ2JzfA4VbLTWnq5qBZctUvx4VkRzJALK6V+5ruJ6CayHoKsR1ueM9oY16WQFLYmUKT1Bu8NI0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fca0c237db2f6493dae2e0b7bc7b6fd770667279b2e7bd3d622913ae402da1ee","last_reissued_at":"2026-07-05T07:41:07.765404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:07.765404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parametric Feature Transfer: One-shot Federated Learning with Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Bie, Guojun Zhang, Leo Maxime Brunswic, Mahdi Beitollahi, Sobhan Hemati, Xi Chen, Xu Li","submitted_at":"2024-02-02T19:34:46Z","abstract_excerpt":"In one-shot federated learning (FL), clients collaboratively train a global model in a single round of communication. Existing approaches for one-shot FL enhance communication efficiency at the expense of diminished accuracy. This paper introduces FedPFT (Federated Learning with Parametric Feature Transfer), a methodology that harnesses the transferability of foundation models to enhance both accuracy and communication efficiency in one-shot FL. The approach involves transferring per-client parametric models (specifically, Gaussian mixtures) of features extracted from foundation models. Subseq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01862","kind":"arxiv","version":1},"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/2402.01862/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":"2402.01862","created_at":"2026-07-05T07:41:07.765463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01862v1","created_at":"2026-07-05T07:41:07.765463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01862","created_at":"2026-07-05T07:41:07.765463+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SQMEN63F5SJ","created_at":"2026-07-05T07:41:07.765463+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SQMEN63F5SJHWXC","created_at":"2026-07-05T07:41:07.765463+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SQMEN63","created_at":"2026-07-05T07:41:07.765463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08368","citing_title":"FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10748","citing_title":"Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25","json":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25.json","graph_json":"https://pith.science/api/pith-number/7SQMEN63F5SJHWXC4C33Y63P25/graph.json","events_json":"https://pith.science/api/pith-number/7SQMEN63F5SJHWXC4C33Y63P25/events.json","paper":"https://pith.science/paper/7SQMEN63"},"agent_actions":{"view_html":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25","download_json":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25.json","view_paper":"https://pith.science/paper/7SQMEN63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01862&json=true","fetch_graph":"https://pith.science/api/pith-number/7SQMEN63F5SJHWXC4C33Y63P25/graph.json","fetch_events":"https://pith.science/api/pith-number/7SQMEN63F5SJHWXC4C33Y63P25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25/action/storage_attestation","attest_author":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25/action/author_attestation","sign_citation":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25/action/citation_signature","submit_replication":"https://pith.science/pith/7SQMEN63F5SJHWXC4C33Y63P25/action/replication_record"}},"created_at":"2026-07-05T07:41:07.765463+00:00","updated_at":"2026-07-05T07:41:07.765463+00:00"}