{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EWKVF5VDFRPYJUZPPMHEDLR4EM","short_pith_number":"pith:EWKVF5VD","schema_version":"1.0","canonical_sha256":"259552f6a32c5f84d32f7b0e41ae3c233f6b23d0a714844e7d9f58210533e6d9","source":{"kind":"arxiv","id":"2407.03247","version":1},"attestation_state":"computed","paper":{"title":"Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenxu Zhao, Fenglong Ma, Jiaqi Wang, Lingjuan Lyu, Mengdi Huai, Quanzeng You","submitted_at":"2024-07-03T16:23:41Z","abstract_excerpt":"This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for information exchange, ensuring model security, and achieving efficient communication simultaneously. To transfer knowledge between large private and small proxy models on clients, we propose a novel uncertainty-based asymmetrical reciprocity learning method, eliminating the need for any public data. Comprehensive experiments conducted on benchmark datase"},"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":"2407.03247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-03T16:23:41Z","cross_cats_sorted":[],"title_canon_sha256":"79b4d7e7953c7017ab53448d8fb3d1b209f2d567621bd19aa93583fed5379dea","abstract_canon_sha256":"554ac3696a1fa1b2544602073f2145d527e90baea77b231a0a4a93d1de5d9dc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:48.272066Z","signature_b64":"F4/oS6/DqlkAEgtrc0+VeZdmpxuu1TVSUn5Nb2C78aU1udebb50EwuqeTSI0rhjKhmvmhWMhlzZxjiqFiIULBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259552f6a32c5f84d32f7b0e41ae3c233f6b23d0a714844e7d9f58210533e6d9","last_reissued_at":"2026-07-05T08:39:48.271660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:48.271660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenxu Zhao, Fenglong Ma, Jiaqi Wang, Lingjuan Lyu, Mengdi Huai, Quanzeng You","submitted_at":"2024-07-03T16:23:41Z","abstract_excerpt":"This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for information exchange, ensuring model security, and achieving efficient communication simultaneously. To transfer knowledge between large private and small proxy models on clients, we propose a novel uncertainty-based asymmetrical reciprocity learning method, eliminating the need for any public data. Comprehensive experiments conducted on benchmark datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03247","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/2407.03247/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":"2407.03247","created_at":"2026-07-05T08:39:48.271717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03247v1","created_at":"2026-07-05T08:39:48.271717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03247","created_at":"2026-07-05T08:39:48.271717+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWKVF5VDFRPY","created_at":"2026-07-05T08:39:48.271717+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWKVF5VDFRPYJUZP","created_at":"2026-07-05T08:39:48.271717+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWKVF5VD","created_at":"2026-07-05T08:39:48.271717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07066","citing_title":"Membership Inference Attacks with False Discovery Rate Control","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM","json":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM.json","graph_json":"https://pith.science/api/pith-number/EWKVF5VDFRPYJUZPPMHEDLR4EM/graph.json","events_json":"https://pith.science/api/pith-number/EWKVF5VDFRPYJUZPPMHEDLR4EM/events.json","paper":"https://pith.science/paper/EWKVF5VD"},"agent_actions":{"view_html":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM","download_json":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM.json","view_paper":"https://pith.science/paper/EWKVF5VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03247&json=true","fetch_graph":"https://pith.science/api/pith-number/EWKVF5VDFRPYJUZPPMHEDLR4EM/graph.json","fetch_events":"https://pith.science/api/pith-number/EWKVF5VDFRPYJUZPPMHEDLR4EM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM/action/storage_attestation","attest_author":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM/action/author_attestation","sign_citation":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM/action/citation_signature","submit_replication":"https://pith.science/pith/EWKVF5VDFRPYJUZPPMHEDLR4EM/action/replication_record"}},"created_at":"2026-07-05T08:39:48.271717+00:00","updated_at":"2026-07-05T08:39:48.271717+00:00"}