Giter Site home page Giter Site logo

ennengyang / adatask Goto Github PK

View Code? Open in Web Editor NEW
21.0 1.0 1.0 15 KB

AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning. AAAI, 2023.

Home Page: https://arxiv.org/abs/2211.15055

Python 100.00%
multi-task-learning multi-objective-optimization negative-transfer adaptive-learning-rate

adatask's Issues

How to Define Shared and Task-Specific Parameters in the PLE Framework

Thank you for sharing your very meaningful work and sharing your codes on this repository. I have a question regarding parameter definition about the PLE framework when using AdaTask.

Could you please provide guidance or examples on how to:

  1. Define shared parameters that are used across all tasks (just shared experts?).
  2. Define task-specific parameters that are unique to each task (task-specific experts and towers?).

I really appreciate your help!!!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.