{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TSAQSJD6FJPLOK7Y3OCLBGFLBN","short_pith_number":"pith:TSAQSJD6","schema_version":"1.0","canonical_sha256":"9c8109247e2a5eb72bf8db84b098ab0b4499e915b883bd4052f1855f0b22c510","source":{"kind":"arxiv","id":"2004.11791","version":2},"attestation_state":"computed","paper":{"title":"Federated learning with hierarchical clustering of local updates to improve training on non-IID data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Briggs, Peter Andras, Zhong Fan","submitted_at":"2020-04-24T15:16:01Z","abstract_excerpt":"Federated learning (FL) is a well established method for performing machine learning tasks over massively distributed data. However in settings where data is distributed in a non-iid (not independent and identically distributed) fashion -- as is typical in real world situations -- the joint model produced by FL suffers in terms of test set accuracy and/or communication costs compared to training on iid data. We show that learning a single joint model is often not optimal in the presence of certain types of non-iid data. In this work we present a modification to FL by introducing a hierarchical"},"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":"2004.11791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-24T15:16:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7e3603165a9c6528c1be0f17b56b00e6e5999805335622ff3f283d8a88cee8b6","abstract_canon_sha256":"f57ccf784d94b87eb3761c6607f36c0d3b8c612496fe5c0455962471c3093fc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:51.038421Z","signature_b64":"pSs27vQWeiDy7F10A1em3xrBWBc8YF4My5Vk/rr20Q0gVE7qTfScvH1yIzvGAU8rB1rgBOAEOk11o9DlG0ayDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8109247e2a5eb72bf8db84b098ab0b4499e915b883bd4052f1855f0b22c510","last_reissued_at":"2026-07-05T01:00:51.037923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:51.037923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated learning with hierarchical clustering of local updates to improve training on non-IID data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Briggs, Peter Andras, Zhong Fan","submitted_at":"2020-04-24T15:16:01Z","abstract_excerpt":"Federated learning (FL) is a well established method for performing machine learning tasks over massively distributed data. However in settings where data is distributed in a non-iid (not independent and identically distributed) fashion -- as is typical in real world situations -- the joint model produced by FL suffers in terms of test set accuracy and/or communication costs compared to training on iid data. We show that learning a single joint model is often not optimal in the presence of certain types of non-iid data. In this work we present a modification to FL by introducing a hierarchical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11791","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/2004.11791/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":"2004.11791","created_at":"2026-07-05T01:00:51.037980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11791v2","created_at":"2026-07-05T01:00:51.037980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11791","created_at":"2026-07-05T01:00:51.037980+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSAQSJD6FJPL","created_at":"2026-07-05T01:00:51.037980+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSAQSJD6FJPLOK7Y","created_at":"2026-07-05T01:00:51.037980+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSAQSJD6","created_at":"2026-07-05T01:00:51.037980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12844","citing_title":"Concurrent vertical and horizontal federated learning with fuzzy cognitive maps","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN","json":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN.json","graph_json":"https://pith.science/api/pith-number/TSAQSJD6FJPLOK7Y3OCLBGFLBN/graph.json","events_json":"https://pith.science/api/pith-number/TSAQSJD6FJPLOK7Y3OCLBGFLBN/events.json","paper":"https://pith.science/paper/TSAQSJD6"},"agent_actions":{"view_html":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN","download_json":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN.json","view_paper":"https://pith.science/paper/TSAQSJD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11791&json=true","fetch_graph":"https://pith.science/api/pith-number/TSAQSJD6FJPLOK7Y3OCLBGFLBN/graph.json","fetch_events":"https://pith.science/api/pith-number/TSAQSJD6FJPLOK7Y3OCLBGFLBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN/action/storage_attestation","attest_author":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN/action/author_attestation","sign_citation":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN/action/citation_signature","submit_replication":"https://pith.science/pith/TSAQSJD6FJPLOK7Y3OCLBGFLBN/action/replication_record"}},"created_at":"2026-07-05T01:00:51.037980+00:00","updated_at":"2026-07-05T01:00:51.037980+00:00"}