{
  "patent_number": "US 12039012",
  "country": "US",
  "title": "Sharing AI Knowledge Between Private Datasets Using Synthetic Data",
  "original_title": "Systems and methods for heterogeneous federated transfer learning",
  "summary": "This patent describes a method for two separate AI systems to share learned information by generating artificial data based on common features, without directly exchanging their private training data.",
  "what_it_does": "This technology allows different AI systems, called \"federated endpoints,\" to learn from each other even when their training data must remain private. It works by first identifying \"shared sample features\" that are common between the first and second training datasets (Claim 1). For example, two hospitals might have patient data, but only the patient's age and gender are shared features. A \"generator\" AI model is trained on the first endpoint using these shared features and other specific data, creating a \"one-hot encoding\" of class labels (Claim 1). This trained generator then produces \"synthetic samples\" (artificial data) that mimic the original data's characteristics. Finally, this generator is used by the second federated endpoint to help it perform its own tasks, like making predictions or classifications (Claim 1). This means the second endpoint gets the benefit of the first endpoint's learning without ever seeing its sensitive raw data.",
  "what_it_does_not_cover": [
    "Does not cover federated learning methods that only exchange model weights or gradients without generating synthetic data.",
    "Does not cover systems where the separate training datasets have no common or 'shared sample features' at all.",
    "Does not cover transferring raw, un-processed training data directly between the federated endpoints.",
    "Does not cover methods that use encoding schemes other than 'one-hot encoding' for the class labels of the shared features.",
    "Does not cover scenarios where a 'generator' is not explicitly trained to produce 'synthetic samples' for inference."
  ],
  "filed": "2021-10-23",
  "granted": "2024-07-16",
  "expires": "2041-10-23",
  "status": "active",
  "holder": "Sharecare AI",
  "holder_url": "https://patentbrief.org/company/sharecare-ai",
  "inventors": [
    {
      "name": "Gabriel Gabra ZACCAK",
      "url": "https://patentbrief.org/inventor/gabriel-gabra-zaccak"
    },
    {
      "name": "Srivatsa Akshay SHARMA",
      "url": "https://patentbrief.org/inventor/srivatsa-akshay-sharma"
    },
    {
      "name": "Salvatore Giuliano VIVONA",
      "url": "https://patentbrief.org/inventor/salvatore-giuliano-vivona"
    },
    {
      "name": "Marina TITOVA",
      "url": "https://patentbrief.org/inventor/marina-titova"
    }
  ],
  "times_cited": 1,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications",
    "healthcare",
    "finance"
  ],
  "abstract": "The technology disclosed relates to a system and method of exporting learned features between federated endpoints whose learning is confined to respective training datasets. The system includes logic to access a first training dataset to train a first federated endpoint and a second training dataset to train a second federated endpoint. The first and second training datasets have first and second sample sets that share one or more shared sample features. The shared sample features are common between the first and second sample sets. The system includes logic to train a first generator on the first federated endpoint. The system includes logic to use the first trained generator for a second inference on a second performance task executed on the second federated endpoint.",
  "url": "https://patentbrief.org/patent/us/12039012/systems-and-methods-for-heterogeneous-federated-transfer-learning",
  "markdown_url": "https://patentbrief.org/patent/us/12039012/systems-and-methods-for-heterogeneous-federated-transfer-learning/md",
  "google_patents_url": "https://patents.google.com/patent/US12039012",
  "relatedPatents": [
    {
      "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": "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"
    },
    {
      "patentNumber": "11915111",
      "countryCode": "US",
      "title": "How Training Systems Share AI Knowledge Without Sharing Private Student Data",
      "url": "https://patentbrief.org/patent/us/11915111/federated-machine-learning-in-adaptive-training-systems"
    },
    {
      "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": "20230297446",
      "countryCode": "US",
      "title": "How to Train AI Models with Fake Data Using Generative Networks",
      "url": "https://patentbrief.org/patent/us/20230297446/data-model-generation-using-generative-adversarial-networks"
    }
  ]
}