Google patents modular AI models that share core skills across tasks
Google describes a system where one large AI model is split into shared parts and specific parts for different jobs. During training, the model learns general skills in the shared section and specific details in the separate sections. When adjusting the model for a new task, it keeps the specific details fixed to prevent the general skills from getting confused or lost.
In the filing’s own words
Provided are systems and methods for generating and/or leveraging a modular multi-domain model. According to one aspect of the present disclosure, the proposed multi-domain model employs a plurality of domain-specific sets of parameters during pre-training to separate domain-specific information from domain-agnostic information. According to another aspect of the present disclosure, the proposed model can overcome the limitations of representation drift during fine-tuning, for example by holding fixed some of the shared parameters (e.g., shared parameters included in the decoder).
What exactly they claim (claim 1)
1. A computer-implemented method to perform improved multi-domain modeling, the method comprising: generating, by a computing system comprising one or more computing devices, a plurality of domain-specific variants of a machine learning model, wherein each of the plurality of domain-specific variants of the machine learning model comprises: a shared set of parameters that are shared among the plurality of domain-specific variants of the machine learning model; and a domain-specific set of parameters that are specific to the domain-specific variant of the machine learning model; training, by the computing system, each of the plurality of domain-specific variants of the machine learning model, wherein said training comprises updating both the shared set of parameters and the domain-specific set of parameters; finetuning, by the computing system, one or more of the plurality of domain-specific variants of the machine learning model, wherein said finetuning comprises updating at least some of the shared set of parameters while holding fixed the domain-specific set of parameters; and providing, by the computing system, the plurality of domain-specific variants of the machine learning model as an output.
Facts
- Company
- Google (Google LLC)
- Official title
- Modular Multi-Domain Machine Learning Models
- Publication number
- US20260310959A1
- Application number
- 19487458
- Filed
- May 22, 2024
- Published
- Oct 8, 2026
- Inventors
- 6
- Claims
- 19
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.