drawbridge/keras-mmoe
A TensorFlow Keras implementation of "Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts" (KDD 2018)
This is a TensorFlow Keras implementation of the Multi-gate Mixture-of-Experts (MMoE) model, designed for developers working with machine learning. It helps you build systems that learn multiple related tasks simultaneously from a single dataset, such as predicting both income and marital status from census data. You input your structured data, and it outputs a model capable of making predictions for several different outcomes, improving efficiency and potentially accuracy. This tool is for machine learning engineers and data scientists building multi-task learning models.
735 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or data scientist looking to implement a multi-task learning model using the MMoE architecture in TensorFlow Keras.
Not ideal if you are an end-user without programming knowledge, or if you need to build a single-task prediction model.
Stars
735
Forks
226
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/drawbridge/keras-mmoe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification