HeGAN
Network embedding framework
A system for learning meaningful representations of nodes in heterogeneous information networks
Source code for KDD 2019 paper "Adversarial Learning on Heterogeneous Information Networks"
70 stars
2 watching
25 forks
Language: Python
last commit: almost 6 years ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
| This repository provides an implementation of a bipartite network embedding algorithm for collaborative filtering and link prediction tasks. | 227 |
| An implementation of Structural Deep Network Embedding using Keras for link prediction and network embedding tasks | 92 |
| Software framework for training and evaluating generative models of images and text based on adversarial networks | 847 |
| A software framework implementing a deep learning-based method to learn embeddings for hyper-networks. | 45 |
| Implementation of a method for generating node embeddings in graph data with attributed information | 160 |
| An implementation of a scalable method for learning node representations in complex networks | 72 |
| This software generates embeddings for nodes in directed networks based on associated text. | 6 |
| An implementation of Community Preserving Network Embedding using deep learning and matrix factorization techniques | 121 |
| A PyTorch implementation of a representation learning framework for dynamic temporal networks | 362 |
| A framework for learning representations from attributed graphs, incorporating structural and attribute information. | 59 |
| A Python library for learning and evaluating knowledge graph embeddings | 1,708 |
| A collection of MATLAB implementations for Generative Adversarial Networks (GANs) and related deep learning techniques | 190 |
| A Common Lisp library for generating word embeddings using neural network models. | 9 |
| A sparsity-aware implementation of a deep learning algorithm for graph embedding with text information. | 74 |
| An implementation of a deep learning-based image representation learning approach using a modified fully connected layer and transfer learning from VGG16 | 34 |