{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3T3Z5FEFOVXBQA6MIUCSIQCIUW","short_pith_number":"pith:3T3Z5FEF","schema_version":"1.0","canonical_sha256":"dcf79e9485756e1803cc4505244048a58908e707acc04443cf5398dabe86ad13","source":{"kind":"arxiv","id":"2408.11304","version":1},"attestation_state":"computed","paper":{"title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Dongqi Cai, Hanzi Mei, Mengwei Xu, Shangguang Wang","submitted_at":"2024-08-21T03:16:12Z","abstract_excerpt":"As Large Language Models (LLMs) push the boundaries of AI capabilities, their demand for data is growing. Much of this data is private and distributed across edge devices, making Federated Learning (FL) a de-facto alternative for fine-tuning (i.e., FedLLM). However, it faces significant challenges due to the inherent heterogeneity among clients, including varying data distributions and diverse task types. Towards a versatile FedLLM, we replace traditional dense model with a sparsely-activated Mixture-of-Experts (MoE) architecture, whose parallel feed-forward networks enable greater flexibility"},"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":"2408.11304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T03:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"e9a1103cbefc323c1e43095e247427bf2303a379e3a58699e9e8d4462aad28dc","abstract_canon_sha256":"559d514bbf22446e2dc3e9451c3d8d6a6e41df1305e7512fac1a86d6d5408e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:41.822795Z","signature_b64":"XOXtx577WdaAPUOe/dTtUhqlhOrKotBF6JAvaJFR9TLM/8RE0uujEo57L+AV5quIl9Z/cAZEdLtpEO0tkizBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcf79e9485756e1803cc4505244048a58908e707acc04443cf5398dabe86ad13","last_reissued_at":"2026-07-05T08:57:41.822380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:41.822380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Dongqi Cai, Hanzi Mei, Mengwei Xu, Shangguang Wang","submitted_at":"2024-08-21T03:16:12Z","abstract_excerpt":"As Large Language Models (LLMs) push the boundaries of AI capabilities, their demand for data is growing. Much of this data is private and distributed across edge devices, making Federated Learning (FL) a de-facto alternative for fine-tuning (i.e., FedLLM). However, it faces significant challenges due to the inherent heterogeneity among clients, including varying data distributions and diverse task types. Towards a versatile FedLLM, we replace traditional dense model with a sparsely-activated Mixture-of-Experts (MoE) architecture, whose parallel feed-forward networks enable greater flexibility"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11304","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/2408.11304/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":"2408.11304","created_at":"2026-07-05T08:57:41.822433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11304v1","created_at":"2026-07-05T08:57:41.822433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11304","created_at":"2026-07-05T08:57:41.822433+00:00"},{"alias_kind":"pith_short_12","alias_value":"3T3Z5FEFOVXB","created_at":"2026-07-05T08:57:41.822433+00:00"},{"alias_kind":"pith_short_16","alias_value":"3T3Z5FEFOVXBQA6M","created_at":"2026-07-05T08:57:41.822433+00:00"},{"alias_kind":"pith_short_8","alias_value":"3T3Z5FEF","created_at":"2026-07-05T08:57:41.822433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":125,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28835","citing_title":"Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":211,"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":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21264","citing_title":"FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW","json":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW.json","graph_json":"https://pith.science/api/pith-number/3T3Z5FEFOVXBQA6MIUCSIQCIUW/graph.json","events_json":"https://pith.science/api/pith-number/3T3Z5FEFOVXBQA6MIUCSIQCIUW/events.json","paper":"https://pith.science/paper/3T3Z5FEF"},"agent_actions":{"view_html":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW","download_json":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW.json","view_paper":"https://pith.science/paper/3T3Z5FEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11304&json=true","fetch_graph":"https://pith.science/api/pith-number/3T3Z5FEFOVXBQA6MIUCSIQCIUW/graph.json","fetch_events":"https://pith.science/api/pith-number/3T3Z5FEFOVXBQA6MIUCSIQCIUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW/action/storage_attestation","attest_author":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW/action/author_attestation","sign_citation":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW/action/citation_signature","submit_replication":"https://pith.science/pith/3T3Z5FEFOVXBQA6MIUCSIQCIUW/action/replication_record"}},"created_at":"2026-07-05T08:57:41.822433+00:00","updated_at":"2026-07-05T08:57:41.822433+00:00"}