# Reading Roadmap for the Beginners

## 0, Tutorials, Books

- AAAI 19 Graph Representation Learning: part-0, part-1, part-2, part-3
- AAAI 20: Graph Neural Networks: Models and Applications
- Jiliang Tang: Deep Learning on Graphs

## 1, Basic GNN model:

- GCN: the most basic model
- Understand GCN in spatial domain: Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
- Understand GCN in spatial domain: Label Efficient Semi-Supervised Learning via Graph Filtering:

## 2, Fundamental of Graph Signal Processing (GSP)

- The Emerging Field of Signal Processing on Graphs [Jouranl Version][Code]
- Vertex-Frequency Analysis on Graphs
- A Tutorial on Spectral Clustering
- Discrete Signal Processing on Graphs
- Design of Graph Filters and Filterbanks
- Discrete Signal Processing on Graphs
- Discrete Signal Processing on Graphs: Frequency Analysis
- Graph Signal Processing: Overview, Challenges, and Applications
- Discrete Signal Processing on Graphs: Sampling Theory
- Signals on Graphs: Uncertainty Principle and Sampling

## 3, Surveys

- Geometric Deep Learning
- Graph Neural Networks: A Review of Methods and Applications
- A Comprehensive Survey on Graph Neural Networks

## 4, Paper Collection

### naganandy/graph-based-deep-learning-literature

master/conference-publications

links to conference publications in graph-based deep learning

### thunlp/GNNPapers

Must-read papers on graph neural networks (GNN). Contribute to thunlp/GNNPapers development by creating an account on GitHub.

## 5, Coding Framework

### rusty1s/pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

### dmlc/dgl

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

## Benchmarks

# References

## Graph Theory

- Graph Theory - Reinhard Diestel
- Graph Theory - J.A. Bondy, U.S.R. Murty
- On the Graph Fourier Transform for Directed Graphs

## Explainable Graph

- GNNExplainer: Generating Explanations for Graph Neural Networks
- Explainability Techniques for Graph Convolutional Networks

- ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions
- NIPS 19: Using Embeddings to Correct for Unobserved Confounding in Networks