/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents method to compress AI models on your phone

Google has filed a patent for a way to run AI models on personal devices by keeping the model's data compressed most of the time. The system only uncompresses small pieces of the data when the phone needs to process them, then immediately deletes the uncompressed version to save memory.

Why it mattersThis technique could help phones and laptops run complex AI features without using up all their memory, making such tools more efficient for everyday users.

In the filing’s own words

Implementations are directed to efficient federated learning of machine learning (ML) model(s) through on-the-fly decompression and compression of model parameters, of the ML model(s), when facilitating forward propagation and/or back propagation at client device(s). For example, implementations can transmit, from a remote system to a client device, a compressed on-device ML model that includes some compressed parameters. Further, the client device can, in performing forward propagation and/or back propagation using the on-device ML model, decompress those compressed parameters on-the-fly as the parameters are needed for the propagation. The propagation will utilize the decompressed parameters that were decompressed on the fly. Further, after the decompressed parameters are utilized, they can be deallocated from memory (while their compressed counterparts optionally remain in memory) to enable allocation of memory for further decompressed parameters that will be needed next and/or needed for other ongoing process(es).

What exactly they claim (claim 1)

1. A client device comprising: memory storing instructions; and one or more processors operable to execute the instructions to: receive a machine learning (ML) model that is in a compressed format and that includes compressed model parameters for processing model input data; for each of multiple compressed subsets of the compressed model parameters of the ML model, to facilitate forward propagation, and while all other of the compressed subsets of parameters of the ML model remain compressed: decompress the compressed subset of parameters to generate a corresponding decompressed subset of parameters; and process corresponding data using the corresponding decompressed subset of parameters to generate a next iteration of the corresponding data and in furtherance of determining a predicted output from the forward propagation; determine, based on the predicted output from the forward propagation, a loss in furtherance of updating the compressed model parameters; for each of multiple compressed subsets of the compressed model parameters of the ML model, to facilitate back propagation, and while all other of the compressed subsets of parameters of the ML model remain compressed: decompress the compressed subset of parameters to generate the corresponding decompressed subset of parameters; process a remaining portion of the loss and the corresponding decompressed subset of parameters to generate corresponding decompressed updated parameters for the corresponding decompressed subset of parameters; compress the corresponding decompressed updated parameters to generate corresponding updated compressed parameters for the ML model; and cause the corresponding updated compressed parameters to be used to update the ML model.

Facts

Company
Google (GOOGLE LLC)
Official title
ON-THE-FLY PARAMETER COMPRESSION AND DECOMPRESSION TO FACILITATE FORWARD AND/OR BACK PROPAGATION AT CLIENTS DURING FEDERATED LEARNING
Publication number
US20260290320A1
Application number
19684783
Filed
May 21, 2026
Published
Sep 24, 2026
Inventors
6
Claims
20

Classified under

G10L 15/063 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

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.