SpreadGNN

Graph learning framework

A framework for decentralized multi-task learning of graph neural networks on molecular data with guaranteed convergence

SpreadGNN: Serverless Multi-Task Learning Framework for Graph Neural Networks. Accepted to AAAI22.

GitHub

44 stars
6 watching
8 forks
Language: Python
last commit: about 4 years ago

Related projects:

RepositoryDescriptionStars
deepgraphlearning/gmnnA software framework that integrates statistical relational learning and graph neural networks for semi-supervised object classification and unsupervised node representation learning.403
yh-yao/fedgcnAn implementation of a federated learning algorithm for training Graph Convolutional Networks on semi-supervised node classification tasks.59
scaleoutsystems/fednAn open source federated learning framework designed to be secure, scalable and easy-to-use for enterprise environments145
mediabrain-sjtu/pfedgraphThis 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
codepothunter/fednpA framework for non-IID federated learning via neural propagation6
melisgl/mglA Common Lisp machine learning library that supports neural networks, Boltzmann machines, and other algorithms.593
mengcz13/kdd2021_cnfgnnAn implementation of a federated graph neural network for spatio-temporal modeling65
gingsmith/fmtlA framework for collaborative learning across multiple tasks and datasets in a distributed manner130
kai-yue/ntk-fedA framework for federated learning that leverages the neural tangent kernel to address statistical heterogeneity in distributed machine learning.3
sungwon-han/fedxAn unsupervised federated learning algorithm that uses cross knowledge distillation to learn meaningful data representations from local and global levels.69
rong-dai/dispflAn implementation of a personalized federated learning framework with decentralized sparse training and peer-to-peer communication protocol.72
mediabrain-sjtu/fedgelaThis project enables federated learning across partially class-disjoint data with curated bilateral curation.11
pengyang7881187/fedrlEnabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data56
ibm/federated-learning-libA framework for collaborative distributed machine learning in enterprise environments.500
yuetan031/fedstarThis project implements a federated learning algorithm for non-IID graph classification tasks by leveraging structural knowledge sharing.60