{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RNAI22Q4Z2BK4MHUUTHP5ULUG6","short_pith_number":"pith:RNAI22Q4","schema_version":"1.0","canonical_sha256":"8b408d6a1cce82ae30f4a4cefed17437ae5b247d4c0ecaddeb7943fdf399cab4","source":{"kind":"arxiv","id":"2111.10192","version":1},"attestation_state":"computed","paper":{"title":"An Expectation-Maximization Perspective on Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Joseph Soriaga, Matthias Reisser, Max Welling","submitted_at":"2021-11-19T12:58:59Z","abstract_excerpt":"Federated learning describes the distributed training of models across multiple clients while keeping the data private on-device. In this work, we view the server-orchestrated federated learning process as a hierarchical latent variable model where the server provides the parameters of a prior distribution over the client-specific model parameters. We show that with simple Gaussian priors and a hard version of the well known Expectation-Maximization (EM) algorithm, learning in such a model corresponds to FedAvg, the most popular algorithm for the federated learning setting. This perspective on"},"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":"2111.10192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T12:58:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"555571e228ee69419496473754ac98e55d434e89c9aa101fd4c062ff5392fce8","abstract_canon_sha256":"749d8958b9afedb9253cfeffec60eb8d4d74a798d0eeeb4f27284fab0a813dee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:29.288788Z","signature_b64":"4xOKTsuA7rYMcw3KViKL9wxrSQKreE2isEDi16Bzrz/Qc0C0X73wHSVzmWULc5hXp/n5Z0q2qvwmNXoyWOacAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b408d6a1cce82ae30f4a4cefed17437ae5b247d4c0ecaddeb7943fdf399cab4","last_reissued_at":"2026-07-05T03:33:29.288272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:29.288272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Expectation-Maximization Perspective on Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Joseph Soriaga, Matthias Reisser, Max Welling","submitted_at":"2021-11-19T12:58:59Z","abstract_excerpt":"Federated learning describes the distributed training of models across multiple clients while keeping the data private on-device. In this work, we view the server-orchestrated federated learning process as a hierarchical latent variable model where the server provides the parameters of a prior distribution over the client-specific model parameters. We show that with simple Gaussian priors and a hard version of the well known Expectation-Maximization (EM) algorithm, learning in such a model corresponds to FedAvg, the most popular algorithm for the federated learning setting. This perspective on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10192","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/2111.10192/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":"2111.10192","created_at":"2026-07-05T03:33:29.288342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10192v1","created_at":"2026-07-05T03:33:29.288342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10192","created_at":"2026-07-05T03:33:29.288342+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNAI22Q4Z2BK","created_at":"2026-07-05T03:33:29.288342+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNAI22Q4Z2BK4MHU","created_at":"2026-07-05T03:33:29.288342+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNAI22Q4","created_at":"2026-07-05T03:33:29.288342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08760","citing_title":"FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6","json":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6.json","graph_json":"https://pith.science/api/pith-number/RNAI22Q4Z2BK4MHUUTHP5ULUG6/graph.json","events_json":"https://pith.science/api/pith-number/RNAI22Q4Z2BK4MHUUTHP5ULUG6/events.json","paper":"https://pith.science/paper/RNAI22Q4"},"agent_actions":{"view_html":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6","download_json":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6.json","view_paper":"https://pith.science/paper/RNAI22Q4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10192&json=true","fetch_graph":"https://pith.science/api/pith-number/RNAI22Q4Z2BK4MHUUTHP5ULUG6/graph.json","fetch_events":"https://pith.science/api/pith-number/RNAI22Q4Z2BK4MHUUTHP5ULUG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6/action/storage_attestation","attest_author":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6/action/author_attestation","sign_citation":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6/action/citation_signature","submit_replication":"https://pith.science/pith/RNAI22Q4Z2BK4MHUUTHP5ULUG6/action/replication_record"}},"created_at":"2026-07-05T03:33:29.288342+00:00","updated_at":"2026-07-05T03:33:29.288342+00:00"}