FedStar
Graph classifier
This project implements a federated learning algorithm for non-IID graph classification tasks by leveraging structural knowledge sharing.
[AAAI'23] Federated Learning on Non-IID Graphs via Structural Knowledge Sharing
60 stars
1 watching
13 forks
Language: Python
last commit: about 2 years ago Related projects:
Repository | Description | Stars |
---|---|---|
| This project enables personalized federated learning with inferred collaboration graphs to improve the performance of machine learning models on non-IID (non-independent and identically distributed) datasets. | 26 |
| Develops an alignment framework for federated learning with non-identical client class sets | 4 |
| Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data | 56 |
| Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift | 81 |
| A Python implementation of Personalized Federated Learning with Graph using PyTorch. | 49 |
| The purpose of this project is to investigate the convergence of a federated learning algorithm on non-IID (non-identically and independently distributed) data. | 255 |
| An implementation of federated learning with prototype-based methods across heterogeneous clients | 134 |
| A PyTorch implementation of a semi-supervised graph classification model that learns hierarchical representations from labeled and unlabeled graph data. | 209 |
| A framework for non-IID federated learning via neural propagation | 6 |
| An unsupervised federated learning algorithm that uses cross knowledge distillation to learn meaningful data representations from local and global levels. | 69 |
| An implementation of a graph classification model using structural attention and PyTorch | 270 |
| An implementation of a federated learning algorithm that generalizes to out-of-distribution scenarios using implicit invariant relationships | 10 |
| An experiment comparing different federated learning approaches for image classification tasks with non-iid datasets. | 8 |
| Evaluates various methods for federated learning on different models and tasks. | 19 |
| This project presents an approach to federated learning that leverages unsupervised techniques to adapt models to unlabeled data without requiring labels. | 33 |