{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JP5UKTIRBUK6XK5UI4NSQ2RG76","short_pith_number":"pith:JP5UKTIR","schema_version":"1.0","canonical_sha256":"4bfb454d110d15ebabb4471b286a26ffabea272ed8efbeebeed2e857fa55654c","source":{"kind":"arxiv","id":"2010.02056","version":3},"attestation_state":"computed","paper":{"title":"Specialized federated learning using a mixture of experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gillblad, Edvin Listo Zec, John Martinsson, Leon Ren\\'e S\\\"utfeld, Olof Mogren","submitted_at":"2020-10-05T14:43:57Z","abstract_excerpt":"In federated learning, clients share a global model that has been trained on decentralized local client data. Although federated learning shows significant promise as a key approach when data cannot be shared or centralized, current methods show limited privacy properties and have shortcomings when applied to common real-world scenarios, especially when client data is heterogeneous. In this paper, we propose an alternative method to learn a personalized model for each client in a federated setting, with greater generalization abilities than previous methods. To achieve this personalization we "},"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":"2010.02056","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"dcf228d885d2c47df8d80037513a7e4ec49d0db3bf1f3a5d60a292b1e22a8139","abstract_canon_sha256":"0c87d049e20ade53b04672357ee4e0910ea0d716eb5430641a30b126f48173db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:18.108124Z","signature_b64":"FHrsdrXqt+oj7N6HQwVfPrKONI6GeTXl1DaMBE97/BgxFS24lztHZ6j//ijiXyZpaUJ7frqw4xjr5jniy5AnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bfb454d110d15ebabb4471b286a26ffabea272ed8efbeebeed2e857fa55654c","last_reissued_at":"2026-07-05T02:13:18.107699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:18.107699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specialized federated learning using a mixture of experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gillblad, Edvin Listo Zec, John Martinsson, Leon Ren\\'e S\\\"utfeld, Olof Mogren","submitted_at":"2020-10-05T14:43:57Z","abstract_excerpt":"In federated learning, clients share a global model that has been trained on decentralized local client data. Although federated learning shows significant promise as a key approach when data cannot be shared or centralized, current methods show limited privacy properties and have shortcomings when applied to common real-world scenarios, especially when client data is heterogeneous. In this paper, we propose an alternative method to learn a personalized model for each client in a federated setting, with greater generalization abilities than previous methods. To achieve this personalization we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02056","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/2010.02056/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":"2010.02056","created_at":"2026-07-05T02:13:18.107772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.02056v3","created_at":"2026-07-05T02:13:18.107772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02056","created_at":"2026-07-05T02:13:18.107772+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP5UKTIRBUK6","created_at":"2026-07-05T02:13:18.107772+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP5UKTIRBUK6XK5U","created_at":"2026-07-05T02:13:18.107772+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP5UKTIR","created_at":"2026-07-05T02:13:18.107772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":154,"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":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76","json":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76.json","graph_json":"https://pith.science/api/pith-number/JP5UKTIRBUK6XK5UI4NSQ2RG76/graph.json","events_json":"https://pith.science/api/pith-number/JP5UKTIRBUK6XK5UI4NSQ2RG76/events.json","paper":"https://pith.science/paper/JP5UKTIR"},"agent_actions":{"view_html":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76","download_json":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76.json","view_paper":"https://pith.science/paper/JP5UKTIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.02056&json=true","fetch_graph":"https://pith.science/api/pith-number/JP5UKTIRBUK6XK5UI4NSQ2RG76/graph.json","fetch_events":"https://pith.science/api/pith-number/JP5UKTIRBUK6XK5UI4NSQ2RG76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76/action/storage_attestation","attest_author":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76/action/author_attestation","sign_citation":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76/action/citation_signature","submit_replication":"https://pith.science/pith/JP5UKTIRBUK6XK5UI4NSQ2RG76/action/replication_record"}},"created_at":"2026-07-05T02:13:18.107772+00:00","updated_at":"2026-07-05T02:13:18.107772+00:00"}