drawbridge/keras-mmoe
A TensorFlow Keras implementation of the Multi-gate Mixture-of-Experts model for multi-task learning from KDD 2018.
Not currently ranked — collecting fresh signals.
star history
This repository provides a Keras-based implementation of the Multi-gate Mixture-of-Experts (MMoE) architecture, a deep learning model that learns relationships between multiple tasks by leveraging shared expert networks with task-specific gating mechanisms. The implementation includes example demonstrations using the UCI census-income dataset and is designed to be extensible for other multi-task learning scenarios.
Frequently asked
- What is drawbridge/keras-mmoe?
- A TensorFlow Keras implementation of the Multi-gate Mixture-of-Experts model for multi-task learning from KDD 2018.
- Is keras-mmoe open source?
- Yes — drawbridge/keras-mmoe is open source, released under the MIT license.
- What language is keras-mmoe written in?
- drawbridge/keras-mmoe is primarily written in Python.
- How popular is keras-mmoe?
- drawbridge/keras-mmoe has 735 stars on GitHub.
- Where can I find keras-mmoe?
- drawbridge/keras-mmoe is on GitHub at https://github.com/drawbridge/keras-mmoe.