{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OUVH2Z2ARGYFAPMMRECYKYFEE2","short_pith_number":"pith:OUVH2Z2A","schema_version":"1.0","canonical_sha256":"752a7d674089b0503d8c89058560a426a55b2e79b345e7d8e2dbb9571cd8037b","source":{"kind":"arxiv","id":"2002.06440","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning with Matched Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Hongyi Wang, Mikhail Yurochkin, Yasaman Khazaeni, Yuekai Sun","submitted_at":"2020-02-15T20:09:24Z","abstract_excerpt":"Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) wi"},"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":"2002.06440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T20:09:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4bfd486ae366c9763be4e11bedc4a29f97060d691896d9ca9e28cc625bfee1cf","abstract_canon_sha256":"c0c134b9560faf4b52ae8ac7638f1bf1e28af75b6d0aa1514573c4cb7036708e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:06.256734Z","signature_b64":"g+TNOe5nwf1ri3TyWhxf5rZ5exC7NsbX8G2UCY8Arpwkurfw+M4oUKrDgpfIIakhXjJ/ZUZn5Hh4RCjNa7ZMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752a7d674089b0503d8c89058560a426a55b2e79b345e7d8e2dbb9571cd8037b","last_reissued_at":"2026-07-05T00:41:06.256339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:06.256339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Matched Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Hongyi Wang, Mikhail Yurochkin, Yasaman Khazaeni, Yuekai Sun","submitted_at":"2020-02-15T20:09:24Z","abstract_excerpt":"Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06440","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/2002.06440/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":"2002.06440","created_at":"2026-07-05T00:41:06.256397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06440v1","created_at":"2026-07-05T00:41:06.256397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06440","created_at":"2026-07-05T00:41:06.256397+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUVH2Z2ARGYF","created_at":"2026-07-05T00:41:06.256397+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUVH2Z2ARGYFAPMM","created_at":"2026-07-05T00:41:06.256397+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUVH2Z2A","created_at":"2026-07-05T00:41:06.256397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06979","citing_title":"Robust Federated Learning Under Real-World Client Churn","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04754","citing_title":"Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25783","citing_title":"Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14951","citing_title":"Flat Channels to Infinity in Neural Loss Landscapes","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2","json":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2.json","graph_json":"https://pith.science/api/pith-number/OUVH2Z2ARGYFAPMMRECYKYFEE2/graph.json","events_json":"https://pith.science/api/pith-number/OUVH2Z2ARGYFAPMMRECYKYFEE2/events.json","paper":"https://pith.science/paper/OUVH2Z2A"},"agent_actions":{"view_html":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2","download_json":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2.json","view_paper":"https://pith.science/paper/OUVH2Z2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06440&json=true","fetch_graph":"https://pith.science/api/pith-number/OUVH2Z2ARGYFAPMMRECYKYFEE2/graph.json","fetch_events":"https://pith.science/api/pith-number/OUVH2Z2ARGYFAPMMRECYKYFEE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2/action/storage_attestation","attest_author":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2/action/author_attestation","sign_citation":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2/action/citation_signature","submit_replication":"https://pith.science/pith/OUVH2Z2ARGYFAPMMRECYKYFEE2/action/replication_record"}},"created_at":"2026-07-05T00:41:06.256397+00:00","updated_at":"2026-07-05T00:41:06.256397+00:00"}