{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q3DNNZBAGOCW4RERGWBCZCUKFE","short_pith_number":"pith:Q3DNNZBA","schema_version":"1.0","canonical_sha256":"86c6d6e42033856e449135822c8a8a292e88954f67a46f8645dd5839bbc2ca90","source":{"kind":"arxiv","id":"2107.06724","version":1},"attestation_state":"computed","paper":{"title":"Federated Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Efstratios Gavves, Matthias Reisser, Max Welling","submitted_at":"2021-07-14T14:15:24Z","abstract_excerpt":"Federated learning (FL) has emerged as the predominant approach for collaborative training of neural network models across multiple users, without the need to gather the data at a central location. One of the important challenges in this setting is data heterogeneity, i.e. different users have different data characteristics. For this reason, training and using a single global model might be suboptimal when considering the performance of each of the individual user's data. In this work, we tackle this problem via Federated Mixture of Experts, FedMix, a framework that allows us to train an ensem"},"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":"2107.06724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-14T14:15:24Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"9314a63689b2a8dfddc0bc0c67f142dd5170ccddab2cbec74391427cc05bd697","abstract_canon_sha256":"39f67a7fc474b312919512d61b7ebd90e67a873a5f1b2734913ab8f3f434b5ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:00.865416Z","signature_b64":"6674UlV3clMVP04JCBcXzQLbY75ZX0hMOqRaOLMNsy6br8eqv/lJo7OvEXENaAGz28/2vdq6/BiTkLK6R7ZFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c6d6e42033856e449135822c8a8a292e88954f67a46f8645dd5839bbc2ca90","last_reissued_at":"2026-07-05T02:58:00.864956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:00.864956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Efstratios Gavves, Matthias Reisser, Max Welling","submitted_at":"2021-07-14T14:15:24Z","abstract_excerpt":"Federated learning (FL) has emerged as the predominant approach for collaborative training of neural network models across multiple users, without the need to gather the data at a central location. One of the important challenges in this setting is data heterogeneity, i.e. different users have different data characteristics. For this reason, training and using a single global model might be suboptimal when considering the performance of each of the individual user's data. In this work, we tackle this problem via Federated Mixture of Experts, FedMix, a framework that allows us to train an ensem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06724","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/2107.06724/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":"2107.06724","created_at":"2026-07-05T02:58:00.865013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.06724v1","created_at":"2026-07-05T02:58:00.865013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06724","created_at":"2026-07-05T02:58:00.865013+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3DNNZBAGOCW","created_at":"2026-07-05T02:58:00.865013+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3DNNZBAGOCW4RER","created_at":"2026-07-05T02:58:00.865013+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3DNNZBA","created_at":"2026-07-05T02:58:00.865013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19025","citing_title":"FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23070","citing_title":"FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02990","citing_title":"FedSQ: Optimized Weight Averaging via Fixed Gating","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE","json":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE.json","graph_json":"https://pith.science/api/pith-number/Q3DNNZBAGOCW4RERGWBCZCUKFE/graph.json","events_json":"https://pith.science/api/pith-number/Q3DNNZBAGOCW4RERGWBCZCUKFE/events.json","paper":"https://pith.science/paper/Q3DNNZBA"},"agent_actions":{"view_html":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE","download_json":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE.json","view_paper":"https://pith.science/paper/Q3DNNZBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.06724&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3DNNZBAGOCW4RERGWBCZCUKFE/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3DNNZBAGOCW4RERGWBCZCUKFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE/action/storage_attestation","attest_author":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE/action/author_attestation","sign_citation":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE/action/citation_signature","submit_replication":"https://pith.science/pith/Q3DNNZBAGOCW4RERGWBCZCUKFE/action/replication_record"}},"created_at":"2026-07-05T02:58:00.865013+00:00","updated_at":"2026-07-05T02:58:00.865013+00:00"}