# How Devices Train Shared AI Models While Keeping Your Data Private > 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. - **Patent:** US 12443890 - **Original title:** Partially local federated learning - **Owner:** Google - **Granted:** 2025 - **Status:** Active - **Times cited:** 0 - **Field:** ai_ml, software, telecommunications, consumer_electronics ## 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. ## The clever bit The novelty lies in the "partially local" approach, where a client device maintains and refines its own unique "local parameters" alongside the shared "global parameters." Critically, it only sends updates for the global parameters, ensuring that its private local data cannot be reconstructed from the transmitted information, a significant privacy enhancement over earlier federated learning methods. ## Real-world examples 1. Predictive text suggestions on smartphones 2. On-device photo categorization and search 3. Voice assistant personalization 4. Personalized recommendation engines 5. Health monitoring applications that train on sensitive user data ## Why it matters This technology is crucial for developing powerful AI models while protecting user privacy. By allowing models to be trained on data directly on user devices, it avoids the need to collect and store sensitive information centrally. This approach helps companies like Google improve services such as predictive keyboards, voice assistants, and photo organization without ever seeing individual user data, which is increasingly important due to data privacy regulations. ## Frequently asked questions ### What does How Devices Train Shared AI Models While Keeping Your Data Private cover? 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. ### Who owns patent US 12443890? Google owns this patent, granted in 2025. ### When does this patent expire? This patent is expected to expire on May 27, 2041, when the invention enters the public domain. ### What problem does this patent solve? This technology is crucial for developing powerful AI models while protecting user privacy. By allowing models to be trained on data directly on user devices, it avoids the need to collect and store sensitive information centrally. This approach helps companies like Google improve services such as predictive keyboards, voice assistants, and photo organization without ever seeing individual user data, which is increasingly important due to data privacy regulations. ### What does this patent NOT cover? Does not cover traditional centralized machine learning where all raw data is sent to a single server for training. **Full plain-English explainer:** https://patentbrief.org/patent/us/12443890/partially-local-federated-learning **Original patent:** https://patents.google.com/patent/US12443890 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [Training AI Models Together with Unlabeled Data Using a Teacher](https://patentbrief.org/patent/us/20220012637/federated-teacher-student-machine-learning) — This patent describes a way for multiple AI systems to learn together from data that hasn't been manually labeled, using a 'teacher' AI to create temporary labels for a 'student' AI. - [Training AI Models Across Different Computers](https://patentbrief.org/patent/us/12574477/distributed-deep-learning-using-a-distributed-deep-neural-network) — This 2026 patent describes a way to train AI models on one computer, send a version to another computer for further training with private data, and then update the original model with the improvements. - [Training AI on Private Data Without Seeing It](https://patentbrief.org/patent/us/12518214/distributed-machine-learning-systems-including-generation-of-synthetic-data) — This patent describes a way to train artificial intelligence models using private data stored on many separate computers, by generating fake data that mimics the real data's patterns, so the private data itself never leaves its original location. - [Adapting AI Models to Fit Device Resources](https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device) — This patent describes how a computer system can automatically shrink a large artificial intelligence model, specifically a "transformer" type, to fit the available computing power of a phone or other device. - [How Cloud Systems Automatically Create and Train AI Data Models](https://patentbrief.org/patent/us/11615208/dall-e-text-to-image-generation) — A cloud-based system that generates fake, privacy-safe data to train AI models, ensuring they remain accurate while protecting sensitive personal information.