Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/tonysy/awesome-graph-networks

Materials for Graph Models and Graph Networks
https://github.com/tonysy/awesome-graph-networks

List: awesome-graph-networks

artificial-intelligence deep-learning probabilistic-graphical-models

Last synced: 6 days ago
JSON representation

Materials for Graph Models and Graph Networks

Awesome Lists containing this project

README

        

# Awesome-Graph-Networks
[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)

Materials for Graph Models and Graph Networks
## 1. Probabilistic Graph Models
- [(Stanford)CS 228: Probabilistic Graphical Models](https://cs.stanford.edu/~ermon/cs228/index.html)
- [[Slides]](https://ermongroup.github.io/cs228-notes/)
- [[Videos]](https://www.youtube.com/playlist?list=PLBAGcD3siRDjiQ5VZQ8t0C7jkHQ8fhuq8)
- [(Coursera)Probabilistic Graphical Models](https://www.coursera.org/learn/probabilistic-graphical-models/)
- [[Slides]](./Course/coursera_probabilistic_graphical_models/slides)

- [(CMU)Probabilistic Graphical Models](http://www.cs.cmu.edu/~epxing/Class/10708/lecture.html)
- Slides are in course homepage
- [[Videos]](https://www.youtube.com/playlist?list=PLI3nIOD-p5aoXrOzTd1P6CcLavu9rNtC-)
## 2. Graph Neural Networks
### (1) Blogs
- [GRAPH CONVOLUTIONAL NETWORKS](http://tkipf.github.io/graph-convolutional-networks/)
A good blog to introduce graph covolutional network

### (2) Papers
- [Relational inductive biases, deep learning, and graph networks(recommend to read first)](https://arxiv.org/pdf/1806.01261.pdf)
- [Semi-Supervised Classification with Graph Convolutional Networks(ICLR 2017)](http://arxiv.org/abs/1609.02907)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NIPS 2016)](https://arxiv.org/abs/1606.09375)

- [Graph Attention Networks (ICLR 2018)](https://arxiv.org/pdf/1710.10903.pdf)
- [Few-shot Learning with Graph Neural Networks (ICLR 2018)](https://arxiv.org/pdf/1711.04043.pdf)

## 3. Comments
### (1) Spectral Approach
Which works with a spectral representations of the graph and have been successfully applied in the context of node classification.
### (2) Non-spectral Approach
Which define convolutions directly on the graph, operating on groups of spatially close neighbors.