{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MIDCMZ27V3X67H3B4IDTLTFHWP","short_pith_number":"pith:MIDCMZ27","schema_version":"1.0","canonical_sha256":"620626675faeefef9f61e20735cca7b3f7a57d708c2fc4f7289e21865fd7fd50","source":{"kind":"arxiv","id":"2006.16765","version":3},"attestation_state":"computed","paper":{"title":"Federated Mutual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Fei Wu, Fengda Zhang, Gang Huang, Jie Zhang, Kun Kuang, Pan Zhou, Tao Shen, Xinkang Jia","submitted_at":"2020-06-27T09:35:03Z","abstract_excerpt":"Federated learning (FL) enables collaboratively training deep learning models on decentralized data. However, there are three types of heterogeneities in FL setting bringing about distinctive challenges to the canonical federated learning algorithm (FedAvg). First, due to the Non-IIDness of data, the global shared model may perform worse than local models that solely trained on their private data; Second, the objective of center server and clients may be different, where center server seeks for a generalized model whereas client pursue a personalized model, and clients may run different tasks;"},"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":"2006.16765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-27T09:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"501c27e782800350dafee1c3e4e39f9991907b40b4a52091388d9a10b0265548","abstract_canon_sha256":"5294ac80de7fbaf195392a39a6daa8ccc28fa2a30d3e8827cd82fe6a9233dc7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:58.253536Z","signature_b64":"RriekhignFHOGfxyKeBmyyOfNyOYkV9I6bzOEfndMMO86NgVBuWdPM7kLVK5cHRi5GIKUcntwbH1WpjAjXVcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620626675faeefef9f61e20735cca7b3f7a57d708c2fc4f7289e21865fd7fd50","last_reissued_at":"2026-07-05T01:35:58.253058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:58.253058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Mutual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Fei Wu, Fengda Zhang, Gang Huang, Jie Zhang, Kun Kuang, Pan Zhou, Tao Shen, Xinkang Jia","submitted_at":"2020-06-27T09:35:03Z","abstract_excerpt":"Federated learning (FL) enables collaboratively training deep learning models on decentralized data. However, there are three types of heterogeneities in FL setting bringing about distinctive challenges to the canonical federated learning algorithm (FedAvg). First, due to the Non-IIDness of data, the global shared model may perform worse than local models that solely trained on their private data; Second, the objective of center server and clients may be different, where center server seeks for a generalized model whereas client pursue a personalized model, and clients may run different tasks;"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16765","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/2006.16765/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":"2006.16765","created_at":"2026-07-05T01:35:58.253114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16765v3","created_at":"2026-07-05T01:35:58.253114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16765","created_at":"2026-07-05T01:35:58.253114+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIDCMZ27V3X6","created_at":"2026-07-05T01:35:58.253114+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIDCMZ27V3X67H3B","created_at":"2026-07-05T01:35:58.253114+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIDCMZ27","created_at":"2026-07-05T01:35:58.253114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13543","citing_title":"Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11919","citing_title":"STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19015","citing_title":"FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP","json":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP.json","graph_json":"https://pith.science/api/pith-number/MIDCMZ27V3X67H3B4IDTLTFHWP/graph.json","events_json":"https://pith.science/api/pith-number/MIDCMZ27V3X67H3B4IDTLTFHWP/events.json","paper":"https://pith.science/paper/MIDCMZ27"},"agent_actions":{"view_html":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP","download_json":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP.json","view_paper":"https://pith.science/paper/MIDCMZ27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16765&json=true","fetch_graph":"https://pith.science/api/pith-number/MIDCMZ27V3X67H3B4IDTLTFHWP/graph.json","fetch_events":"https://pith.science/api/pith-number/MIDCMZ27V3X67H3B4IDTLTFHWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP/action/storage_attestation","attest_author":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP/action/author_attestation","sign_citation":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP/action/citation_signature","submit_replication":"https://pith.science/pith/MIDCMZ27V3X67H3B4IDTLTFHWP/action/replication_record"}},"created_at":"2026-07-05T01:35:58.253114+00:00","updated_at":"2026-07-05T01:35:58.253114+00:00"}