Fully Homomorphic Encryption for Private Federated Learning

Batchman and Robin in the paper: "Batchman and Robin: Batched and Non-batched Branching for Interactive ZK"

Efficient and Interactive Zero-Knowledge Proofs

图神经网络、图卷积网络、图注意力网络、图自编码网络、时空图神经网络等论文合集。

《深入浅出图神经网络：GNN原理解析》配套代码

Implementation of Federated Learning using Graph Neural Networks

Codes about Graph Neural Networks and Federated Learning

A development of a Federated Learning (FL) setting for Graph Neural Networks (GNNs) in which data privacy is maintained, and its applicability in different federation types and graph-related tasks.

Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

The official implementation of the DGA-GNN algorithm.

The code for "Deep Contrastive Graph Learning with Clustering-Oriented Guidance" (AAAI24).

Official repo of the paper "No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation" accepted in AAAI 2024

Efficient and Straggler-Resistant Homomorphic Encryption for Heterogeneous Federated Learning

OpenFHE-Based Examples of Logistic Regression Training using Nesterov Accelerated Gradient Descent

PyTorch extension to enable training and testing using homomorphic encryption

Official mirror of Python-FHEz; Python Fully Homomorphic Encryption (FHE) Library for Encrypted Deep Learning as a Service (EDLaaS).

Demonstrate the Federated Learning with different Homomorphic Encryption techniques on neural network models

Flower framework for Federated Learning, with Fully Homomorphic Encryption integrated

Federated learning with Fully Homomorphic Encryption

Federated learning with homomorphic encryption enables multiple parties to securely co-train artificial intelligence models in pathology and radiology, reaching state-of-the-art performance with pr…

Homomorphic Encryption and Federated Learning based Privacy-Preserving