{
  "patent_number": "US 12443890",
  "country": "US",
  "title": "How Devices Train Shared AI Models While Keeping Your Data Private",
  "original_title": "Partially local federated learning",
  "summary": "This patent describes a method for training a machine learning model across many devices, where each device keeps some parts of the model and its data private, only sharing updates for the common, global parts of the model.",
  "what_it_does": "This patent outlines a method for a client device to help train a larger machine learning model without sending its private data to a central server. The model has two parts: \"local parameters\" unique to the client, and \"global parameters\" shared across all devices. The client first receives the current global parameters from a server. Then, using a \"support dataset\" (a part of its local data not used for global training), it figures out the best values for its own local parameters (Claim 1). After that, it uses a \"query dataset\" (another part of its local data) to train and update only the global parameters (Claim 1). Finally, it sends back only the changes to the global parameters, specifically designed so that the server cannot reconstruct the client's private local data or local parameters (Claim 1). For example, your phone could help improve a predictive text model by training it on your typing habits, but only send back general improvements to the shared dictionary, never your specific messages.",
  "what_it_does_not_cover": [
    "Does not cover traditional centralized machine learning where all raw data is sent to a single server for training.",
    "Does not cover federated learning systems that only have global parameters and no distinct local parameters on the client device.",
    "Does not cover methods where the client computing device transmits updates to its local parameters to the server.",
    "Does not cover systems where the parameter update data allows for the recovery of the local data maintained at the client device.",
    "Does not cover training methods that do not partition the local data into separate \"support\" and \"query\" datasets for different training steps."
  ],
  "filed": "2021-05-27",
  "granted": "2025-10-14",
  "expires": "2041-05-27",
  "status": "active",
  "holder": "Google",
  "holder_url": "https://patentbrief.org/company/google",
  "inventors": [
    {
      "name": "Karan Singhal",
      "url": "https://patentbrief.org/inventor/karan-singhal"
    },
    {
      "name": "Hakim Sidahmed, JR.",
      "url": "https://patentbrief.org/inventor/hakim-sidahmed-jr"
    },
    {
      "name": "Zachary A. Garrett",
      "url": "https://patentbrief.org/inventor/zachary-a-garrett"
    },
    {
      "name": "Shanshan WU",
      "url": "https://patentbrief.org/inventor/shanshan-wu"
    },
    {
      "name": "John Keith Rush",
      "url": "https://patentbrief.org/inventor/john-keith-rush"
    },
    {
      "name": "Sushant Prakash",
      "url": "https://patentbrief.org/inventor/sushant-prakash"
    }
  ],
  "times_cited": 0,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications",
    "consumer_electronics"
  ],
  "abstract": "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model having a set of local model parameters and a set of global model parameters under a partially local federated learning framework. One of the methods include maintaining local data and data defining the local model parameters; receiving data defining current values of the global model parameters; determining, based on the local data, the local model parameters, and the current values of the global model parameters, current values of the local model parameters; determining, based on the local data, the current values of the local model parameters, and the current values of the global model parameters, updated values of the global model parameters; generating, based on the updated values of the global model parameters, parameter update data defining an update to the global model parameters; and transmitting the parameter update data.",
  "url": "https://patentbrief.org/patent/us/12443890/partially-local-federated-learning",
  "markdown_url": "https://patentbrief.org/patent/us/12443890/partially-local-federated-learning/md",
  "google_patents_url": "https://patents.google.com/patent/US12443890",
  "relatedPatents": [
    {
      "patentNumber": "20220012637",
      "countryCode": "US",
      "title": "Training AI Models Together with Unlabeled Data Using a Teacher",
      "url": "https://patentbrief.org/patent/us/20220012637/federated-teacher-student-machine-learning"
    },
    {
      "patentNumber": "12574477",
      "countryCode": "US",
      "title": "Training AI Models Across Different Computers",
      "url": "https://patentbrief.org/patent/us/12574477/distributed-deep-learning-using-a-distributed-deep-neural-network"
    },
    {
      "patentNumber": "12518214",
      "countryCode": "US",
      "title": "Training AI on Private Data Without Seeing It",
      "url": "https://patentbrief.org/patent/us/12518214/distributed-machine-learning-systems-including-generation-of-synthetic-data"
    },
    {
      "patentNumber": "20220383078",
      "countryCode": "US",
      "title": "Adapting AI Models to Fit Device Resources",
      "url": "https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device"
    },
    {
      "patentNumber": "11615208",
      "countryCode": "US",
      "title": "How Cloud Systems Automatically Create and Train AI Data Models",
      "url": "https://patentbrief.org/patent/us/11615208/dall-e-text-to-image-generation"
    }
  ]
}