Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. a new neural network model has proposed, which called graph neural network (GNN)
- paper: SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS
- paper: Relational inductive biases, deep learning, and graph networks
- paper: Graph Neural Networks: A Review of Methods and Applications
- paper: Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
- paper: A Comparison between Recursive Neural Networks and Graph Neural Networks
- paper: Spectral Networks and Deep Locally Connected Networks on Graphs
- paper: Wavelets on Graphs via Spectral Graph Theory
- paper: A Comprehensive Survey on Graph Neural Networks
- paper: Variational Graph Auto-Encoders
- paper: Tensor Graph Convolutional Networks for Prediction on Dynamic Graphs
- paper: An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information
- paper: Hypergraph Neural Networks
- paper: Hypergraph Convolution and Hypergraph Attention
- paper:
☆ Deep Learning on Graphs (a Tutorial)
☆ The graph neural network model
☆ Must-read papers on GNN
☆ A Gentle Introduction to Graph Neural Networks (Basics, DeepWalk, and GraphSage); by Steeve Huang
☆ Tutorial on Graph Neural Networks for Computer Vision and Beyond (Part1), by Boris Knyazev
☆ Graph Neural Network - Papers With Code
☆ Tutorial on Variational Graph Auto-Encoders
☆ Connection and separation in hypergraphs, Theory and Applications of Graphs.
☕ Graph Convolutional Networks by Thomas Kipf
☕ Can we do better than Convolutional Neural Networks?, by Boris Knyazev
☕ paper: Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
☕ paper: Bayesian graph convolutional neural networks for semi-supervised classification
☕ paper: A deep convolutional neural network for classification of red blood cells in sickle cell anemia
- How to do Deep Learning on Graphs with Graph Convolutional Networks by Tobias Skovgaard Jepsen
- Deep Graph Library (DGL) is a Python package built for easy implementation of graph neural network model family, on top of existing DL frameworks (e.g. PyTorch, MXNet, Gluon etc.).
- graph_nets - module reference
- A collection of various deep learning models for TensorFlow and PyTorch in Jupyter Notebooks.
- A tutorial on graph neural network with CODE
- Hands-on Graph Neural Networks with PyTorch & PyTorch Geometric
- Sage Reference Manual: Graph Theory (The Sage Development Team)
☕ Machine Learning with Graphs, (Stanford / Fall 2019)
☕
♦ A Repository of Benchmark Graph Datasets for Graph Classification
♦ Network Repository. A Scientific Network Data Repository with Interactive Visualization and Mining Tools
♦ SimGNN
♦ The House of Graphs; Database of interesting graphs
- All graphs in Sage can be built through Common Graphs.
- PyGraphviz is a Python interface to the Graphviz graph layout and visualization package.
-
Solving NP-Hard and NP-Complete Problems in Combinatorics
- A Graph Neural Network for Decision TSP (Traveling Salesperson Problem)
- classic NP-hard problems, such as Satisfiability, Travelling Salesman, Knapsack, Minimum Vertex Cover, and Maximum Cut