Google patents method to cut data transfer in distributed AI training
Google describes a system for training AI models across many devices without sending all the data to a central server. It works by sending only a small part of the model's settings to each device, while the rest is rebuilt locally using a shared starting number.
In the filing’s own words
Example aspects of the present disclosure provide a novel, resource-efficient approach for federated machine learning techniques with PTNs. The system can determine a first set of training parameters from a plurality of parameters of the global model. Additionally, the system can generate a random seed, using a random number generator, based on a set of frozen parameters. Moreover, the system can transmit, respectively to a plurality of client computing devices, a first set of training parameters and the random seed. Furthermore, the system can receive, respectively from the plurality of client computing devices, updates to one or more parameters in the first set of training parameters. Subsequently, the system can aggregate the updates to one or more parameters that are respectively received from the plurality of client computing devices. The system can modify one or more global parameters of the global model based on the aggregation.
What exactly they claim (claim 1)
1. A computer-implemented method for federated learning of a global model with improved communication efficiency, the method comprising: determining, by a server computing system, a first set of training parameters from a plurality of parameters of the global model, wherein the plurality of parameters of the global model includes the first set of training parameters and a set of frozen parameters; transmitting, by the server computing system, respectively to a plurality of client computing devices, the first set of training parameters and an initialization value, wherein the set of frozen parameters are reconstructed from the initialization value by the plurality of client computing devices; receiving, by the server computing system, respectively from the plurality of client computing devices, updates to one or more parameters in the first set of training parameters, wherein the updates to one or more parameters were generated respectively by the plurality of computing devices using a local model stored respectively in the plurality of client computing devices; aggregating by the server computing system, the updates to one or more parameters that are respectively received from the plurality of client computing devices; and modifying by the server computing system, one or more global parameters of the global model based on the aggregation of the updates to the one or more parameters that are respectively received from the plurality of client computing devices.
Facts
- Company
- Google (Google LLC)
- Official title
- Federated learning with partially trainable networks
- Patent number
- US12762393B2
- Application number
- 17568933
- Filed
- Jan 5, 2022
- Granted
- Oct 13, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06N 3/08 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.