{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LGMZ7T23VDKPPTNTVUEYA5LA5A","short_pith_number":"pith:LGMZ7T23","schema_version":"1.0","canonical_sha256":"59999fcf5ba8d4f7cdb3ad09807560e83dcc2dd325bc1181d4792721d548290c","source":{"kind":"arxiv","id":"2009.07999","version":3},"attestation_state":"computed","paper":{"title":"Distilled One-Shot Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dapeng Wu, George Pu, Xiaolin Li, Xiyao Ma, Yanlin Zhou","submitted_at":"2020-09-17T01:14:47Z","abstract_excerpt":"Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. Inspired by recent work on dataset distillation and distributed one-shot learning, we propose Distilled One-Shot Federated Learning (DOSFL) to significantly reduce the communication cost while achieving comparable performance. In just one round, each client distills their private dataset, sends the synthetic data (e.g. images or sentences) to the server, and collectively trains a global model. The distilled data look"},"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":"2009.07999","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-17T01:14:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b535c174362844ddb259b94d1d0ab43e8f46856d9fb7d1a30225070a936fa0c","abstract_canon_sha256":"6193a9a7e53f176e993956835520121069aa56db6e5fb9adce2a3a4c37834a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:24.427874Z","signature_b64":"3pacJyKqUyf4AkEcCvwtyjdj2FFZbCxSLPpNxNq0cuaQ4Rh88e0ooZ3WfJO677MP+TppN+RvA7JszcBY0VUmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59999fcf5ba8d4f7cdb3ad09807560e83dcc2dd325bc1181d4792721d548290c","last_reissued_at":"2026-07-05T02:46:24.427393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:24.427393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilled One-Shot Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dapeng Wu, George Pu, Xiaolin Li, Xiyao Ma, Yanlin Zhou","submitted_at":"2020-09-17T01:14:47Z","abstract_excerpt":"Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. Inspired by recent work on dataset distillation and distributed one-shot learning, we propose Distilled One-Shot Federated Learning (DOSFL) to significantly reduce the communication cost while achieving comparable performance. In just one round, each client distills their private dataset, sends the synthetic data (e.g. images or sentences) to the server, and collectively trains a global model. The distilled data look"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.07999","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/2009.07999/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":"2009.07999","created_at":"2026-07-05T02:46:24.427458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.07999v3","created_at":"2026-07-05T02:46:24.427458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.07999","created_at":"2026-07-05T02:46:24.427458+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGMZ7T23VDKP","created_at":"2026-07-05T02:46:24.427458+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGMZ7T23VDKPPTNT","created_at":"2026-07-05T02:46:24.427458+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGMZ7T23","created_at":"2026-07-05T02:46:24.427458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01901","citing_title":"FedBiCross: Personalized One-Shot Federated Learning on Medical Images","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10748","citing_title":"Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00578","citing_title":"Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A","json":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A.json","graph_json":"https://pith.science/api/pith-number/LGMZ7T23VDKPPTNTVUEYA5LA5A/graph.json","events_json":"https://pith.science/api/pith-number/LGMZ7T23VDKPPTNTVUEYA5LA5A/events.json","paper":"https://pith.science/paper/LGMZ7T23"},"agent_actions":{"view_html":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A","download_json":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A.json","view_paper":"https://pith.science/paper/LGMZ7T23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/LGMZ7T23VDKPPTNTVUEYA5LA5A/graph.json","fetch_events":"https://pith.science/api/pith-number/LGMZ7T23VDKPPTNTVUEYA5LA5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A/action/storage_attestation","attest_author":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A/action/author_attestation","sign_citation":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A/action/citation_signature","submit_replication":"https://pith.science/pith/LGMZ7T23VDKPPTNTVUEYA5LA5A/action/replication_record"}},"created_at":"2026-07-05T02:46:24.427458+00:00","updated_at":"2026-07-05T02:46:24.427458+00:00"}