{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7TSXNBKGR7YHYI32AYAJKTCH7U","short_pith_number":"pith:7TSXNBKG","schema_version":"1.0","canonical_sha256":"fce57685468ff07c237a0600954c47fd3da0acb74ddda4d736410d45c16e3264","source":{"kind":"arxiv","id":"2110.03469","version":3},"attestation_state":"computed","paper":{"title":"Federated Learning from Small Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jilles Vreeken, Jonas Fischer, Michael Kamp","submitted_at":"2021-10-07T13:49:23Z","abstract_excerpt":"Federated learning allows multiple parties to collaboratively train a joint model without sharing local data. This enables applications of machine learning in settings of inherently distributed, undisclosable data such as in the medical domain. In practice, joint training is usually achieved by aggregating local models, for which local training objectives have to be in expectation similar to the joint (global) objective. Often, however, local datasets are so small that local objectives differ greatly from the global objective, resulting in federated learning to fail. We propose a novel approac"},"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":"2110.03469","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T13:49:23Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"5f0a56c5fb78af61cbb27b0bea9f7ffed83c44b2a762b4c548a8799b959e7511","abstract_canon_sha256":"1b6a8e6a9904d7302bb4524f9d5cfcc6d9b027133129f8591fcbc659051bf60c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:05.790856Z","signature_b64":"NVM7tNRR++vG1ihVsNah9fP/g81o8fYILq8f7Ds9WMpyt4PAoUZ2pDr5XJ0GxxiD3txubSdpU4VDPOV/wm/JBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fce57685468ff07c237a0600954c47fd3da0acb74ddda4d736410d45c16e3264","last_reissued_at":"2026-07-05T07:00:05.790386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:05.790386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning from Small Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jilles Vreeken, Jonas Fischer, Michael Kamp","submitted_at":"2021-10-07T13:49:23Z","abstract_excerpt":"Federated learning allows multiple parties to collaboratively train a joint model without sharing local data. This enables applications of machine learning in settings of inherently distributed, undisclosable data such as in the medical domain. In practice, joint training is usually achieved by aggregating local models, for which local training objectives have to be in expectation similar to the joint (global) objective. Often, however, local datasets are so small that local objectives differ greatly from the global objective, resulting in federated learning to fail. We propose a novel approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03469","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/2110.03469/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":"2110.03469","created_at":"2026-07-05T07:00:05.790438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03469v3","created_at":"2026-07-05T07:00:05.790438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03469","created_at":"2026-07-05T07:00:05.790438+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TSXNBKGR7YH","created_at":"2026-07-05T07:00:05.790438+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TSXNBKGR7YHYI32","created_at":"2026-07-05T07:00:05.790438+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TSXNBKG","created_at":"2026-07-05T07:00:05.790438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08508","citing_title":"SFedKD: Sequential Federated Learning with Discrepancy-Aware Multi-Teacher Knowledge Distillation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U","json":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U.json","graph_json":"https://pith.science/api/pith-number/7TSXNBKGR7YHYI32AYAJKTCH7U/graph.json","events_json":"https://pith.science/api/pith-number/7TSXNBKGR7YHYI32AYAJKTCH7U/events.json","paper":"https://pith.science/paper/7TSXNBKG"},"agent_actions":{"view_html":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U","download_json":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U.json","view_paper":"https://pith.science/paper/7TSXNBKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03469&json=true","fetch_graph":"https://pith.science/api/pith-number/7TSXNBKGR7YHYI32AYAJKTCH7U/graph.json","fetch_events":"https://pith.science/api/pith-number/7TSXNBKGR7YHYI32AYAJKTCH7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U/action/storage_attestation","attest_author":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U/action/author_attestation","sign_citation":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U/action/citation_signature","submit_replication":"https://pith.science/pith/7TSXNBKGR7YHYI32AYAJKTCH7U/action/replication_record"}},"created_at":"2026-07-05T07:00:05.790438+00:00","updated_at":"2026-07-05T07:00:05.790438+00:00"}