DBE
by TsingZ0
NeurIPS 2023 accepted paper, Eliminating Domain Bias for Federated Learning in Representation Space
AI summary
Domain adaptation library
An implementation of a federated learning method to reduce domain bias in representation space, enabling improved knowledge transfer between clients and servers.
- stars
- 22
- forks
- 1
- watching
- 2
Similar projects
Found by comparing what the projects do, not just their names.
Fed learning library
An implementation of a federated learning method for personalized models on non-iid datasets.
Domain adaptation
Improves federated learning performance by incorporating domain knowledge and regularization to adapt models across diverse domains
Feature separator
A framework that separates feature information from data in federated learning to enable personalized models.
Domain generalization method
This project presents a method for federated domain generalization with adjustment, allowing multiple models to learn from each other across different domains.
Federated learner
Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift
Heterogeneity fixer
Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation
Federated learner optimizer
A tool for training federated learning models with adaptive gradient balancing to handle class imbalance in multi-client scenarios.
Federated Learning Algorithm
This project presents an approach to federated learning with partial client participation by optimizing anchor selection for improving model accuracy and convergence.
Bias detection tool
This project investigates how bias can be introduced and spread in machine learning models during federated learning, and aims to detect and mitigate this issue.
Flat minimization optimizer
Improving generalization in federated learning by seeking flat minima through optimization techniques
Federated Learning Algorithm
An implementation of federated learning algorithm to reduce local learning bias and improve convergence on heterogeneous data
Domain adaptation model
This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another.
Federated learner
Provides code for a federated learning algorithm to optimize machine learning models in a distributed setting.
Domain adaptation algorithm
Develops object detection algorithms to adapt to new domains with limited supervision
Federated Learner
An implementation of a federated learning algorithm that generalizes to out-of-distribution scenarios using implicit invariant relationships
