{
  "id": "enwiki-001378647925",
  "slug": "federated-learning",
  "title": "Federated learning",
  "qid": "",
  "lead": "Federated learning (also known as collaborative learning) is a machine learning technique in a setting where multiple entities (often called clients) collaboratively train a model while keeping their data decentralized, rather than centrally stored. A defining characteristic of federated learning is data heterogeneity. Because client data is decentralized, data samples held by each client may not be independently and identically distributed. Federated learning is generally concerned with and motivated by issues such as data privacy, data minimization, and data access rights. Its applications involve a variety of research areas including defence, telecommunications, the Internet of things, and pharmaceuticals.",
  "body": "Federated learning (also known as collaborative learning) is a machine learning technique in a setting where multiple entities (often called clients) collaboratively train a model while keeping their data decentralized, rather than centrally stored. A defining characteristic of federated learning is data heterogeneity. Because client data is decentralized, data samples held by each client may not be independently and identically distributed. Federated learning is generally concerned with and motivated by issues such as data privacy, data minimization, and data access rights. Its applications involve a variety of research areas including defence, telecommunications, the Internet of things, and pharmaceuticals. f(\\mathbf x_1, \\dots, \\mathbf x_K) = \\dfrac{1}{K} \\sum_{i=1}^K f_i(\\mathbf x_i) where K is the number of nodes, \\mathbf x_i are the weights of model as viewed by node i , and f_i is node i 's local objective function, which describes how model weights \\mathbf x_i conforms to node i 's local dataset. The goal of federated learning is to train a common model on all of the nodes' local datasets, in other words: Optimizing the objective function f(\\mathbf x_1, \\dots, \\mathbf x_K) . Achieving consensus on \\mathbf x_i . In other words, \\mathbf x_1, \\dots, \\mathbf x_K converge to some common \\mathbf x at the end of the training process. \"Regulation (EU) 2016/679 of the European Parliament and of the Council of 27 April 2016\" at eur-lex.europa.eu. Retrieved October 18, 2019. \"Data minimisation and privacy-preserving techniques in AI systems\" at UK Information Commissioners Office. Retrieved July 22, 2020 \"Realising the Potential of Data Whilst Preserving Privacy with EyA and Conclave from R3\" at eya.global. Retrieved March 31, 2022.",
  "categories": [
    "22921972",
    "23118434",
    "23603337",
    "24623845",
    "90495183"
  ],
  "license": "CC BY-SA 4.0",
  "source_uri": "https://en.wikipedia.org/w/index.php?oldid=1378647925",
  "content_hash": "",
  "created_at": null,
  "updated_at": 1791197086.0,
  "claims": [],
  "contradictions": [],
  "confidence": 0.6,
  "csl": {
    "id": "enwiki-001378647925",
    "type": "webpage",
    "title": "Federated learning",
    "author": [
      {
        "family": "Anticloud FZ LLE",
        "literal": "Anticloud FZ LLE"
      }
    ],
    "container-title": "encyclopegia.org",
    "publisher": "Anticloud FZ LLE",
    "publisher-place": "Dubai, United Arab Emirates",
    "URL": "https://encyclopegia.org/a/federated-learning",
    "issued": {
      "date-parts": [
        [
          2026,
          11,
          21
        ]
      ]
    },
    "accessed": {
      "date-parts": [
        [
          2026,
          11,
          21
        ]
      ]
    },
    "license": "CC BY-SA 4.0",
    "DOI": "eo1:enwiki-001378647925",
    "isBasedOn": "https://en.wikipedia.org/w/index.php?oldid=1378647925",
    "note": "Immutable snapshot enwiki-001378647925"
  }
}