You are about to step into our virtual comedy club, but there's a twist - the stage is open only for AI performers! In this challenge, your task is to develop a unique AI performer (a chatbot), who…

gnn for link prediction，图神经网络用于链接预测。

Some GNNs are implemented using PyG for node classification tasks, including: GCN, GraphSAGE, SGC, GAT, R-GCN and HAN (Heterogeneous Graph Attention Network), which will continue to be updated in t…

Python package built to ease deep learning on graph, on top of existing DL frameworks.

A curated list of adversarial attacks and defenses papers on graph-structured data.

Code for the paper "Quantifying Privacy Leakage in Graph Embedding" published in MobiQuitous 2020

This repository aims to provide links to works about privacy attacks and privacy preservation on graph data with Graph Neural Networks (GNNs).

Official Code Repository for the paper "Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations" (ICML 2022)

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation (USENIX Security '23)

(CIKM'21) Variational Graph Normalized Auto-Encoders

Code for the paper "RWR-GAE: Random Walk Regularized Graph Auto Encoder"

Source code and dataset for KDD 2020 paper "Adaptive Graph Encoder for Attributed Graph Embedding"

Source code of attributed graph generator

Code for paper Unsupervised Attributed Network Embedding via Cross Fusion (WSDM 2021)

Scalable and privacy-enhanced graph generative models for benchmark graph neural networks

How to convert MDS trip data to anonymized open data for city governments.

Workspace for the OMF's Privacy, Security, and Transparency Committee

Code for KDD'20 "Generative Pre-Training of Graph Neural Networks"

The source code of our ACM MM 2019 paper "TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning".

Official implementation of "GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators" (NeurIPS 2020)

PPGANs: Privacy-preserving Generative Adversarial Networks.

Google's differential privacy libraries.

Implementation of the paper "NetGAN: Generating Graphs via Random Walks".

A graphical user interface for machine learning built on streamlit and pycaret