Graph-Embedding-Techniques

It provides some interesting graph embedding techniques based on task-free or task-specific intuitions.

Table of Contents

1. Pure Network Embedding
   • 1.1. Node Proximity Relationship
   • 1.2. Structural Identity
2. Attributed Network Embedding
   • 2.1. Attribute Vectors
   • 2.2. Text Content
3. Graph Neural Networks
   • 3.1. Node Classification
   • 3.2. Graph Classification
   • 3.3. Link Prediction
   • 3.4. Community Detection
   • 3.5. Rare Category Characterization
4. Graph Kernels

1. Pure Network Embedding

1.1. Node Proximity Relationship

• DeepWalk: Online Learning of Social Representations (KDD'14). [Paper] [Python Code]

• **LINE: Large-scale Information Network Embedding (http://www.www2015.it/documents/proceedings/proceedings/p1067.pdfproceedings/p1067.pdf) [C++ Code]

• node2vec: Scalable Feature Learning for Networks (KDD'16). [Paper] [Project][Python Code]

• Watch Your Step: Learning Node Embeddings via Graph Attention (NIPS'18). [Paper] [Python Code]

• Deep Graph Infomax (ICLR'19). [Paper] [OpenReview] [Code]

1.2. Structural Identity

• struc2vec: Learning Node Representations from Structural Identity (KDD'17). [Paper] [Python Code]

• Learning Structural Node Embeddings via Diffusion Wavelets (KDD'18). [Paper] [Project] [Python Code]

2. Attributed Network Embedding

2.1 Attribute Vectors

• Label Informed Attributed Network Embedding (WSDM'17). [Paper] [MATLAB Code]

• Accelerated Attributed Network Embedding (SDM'17). [Paper] [Python Code] [MATLAB Code]

• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (ICLR'18). [Paper][OpenReview] [Python Code]

2.2. Text Content

• Network Representation Learning with Rich Text Information (IJCAI'15). [Paper] [MATLAB Code]

• CANE: Context-Aware Network Embedding for Relation Modeling (ACL'17). [Paper] [Python Code]

• Diffusion Maps for Textual Network Embedding (NIPS'18). [Paper] [Python Code]

3. Graph Neural Networks

3.1. Node Classification

• Diffusion-Convolutional Neural Networks (NIPS'16). [Paper] [Code]

• Geometric Deep Learning: Going beyond Euclidean data (SPM'17). [Paper] [Project]

• Inductive Representation Learning on Large Graphs (NIPS'17). [Paper] [Project] [Code]

• Semi-Supervised Classification with Graph Convolutional Networks (ICLR'17). [Paper][OpenReview] [Code]

• Neural Message Passing for Quantum Chemistry (ICML'17). [Paper] [Code]

• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning (AAAI'18). [Paper] [Code]

• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling (ICLR'18). [Paper][OpenReview] [Code]

• Stochastic Training of Graph Convolutional Networks with Variance Reduction (ICML'18). [Paper] [Code]

• Graph Attention Networks (ICLR'18). [Paper][OpenReview] [Code]

• Relational Inductive Biases, Deep Learning, and Graph Networks (arXiv'18). [Paper] [Code]

3.2. Graph Classification

• Learning Convolutional Neural Networks for Graphs (ICML'16). [Paper] [Code]

• Deriving Neural Architectures from Sequence and Graph Kernels (ICML'17). [Paper] [Code]

• An End-to-End Deep Learning Architecture for Graph Classification (AAAI'18). [Paper] [Code]

• Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks (AAAI'19). [Paper] [Code]

• How Powerful are Graph Neural Networks? (ICLR'19). [Paper][OpenReview][Code]

• Capsule Graph Neural Network (ICLR'19). [Paper][OpenReview][Code]

3.3. Link Prediction

• Link Prediction Based on Graph Neural Networks (NIPS'18). [Paper] [Code]

3.4. Community Detection

• Supervised Community Detection with Line Graph Neural Networks (ICLR'19). [Paper] [OpenReview] [Code]

3.5. Rare Category Characterization

• SPARC: Self-Paced Network Representation for Few-Shot Rare Category Characterization (KDD'18). [Paper] [Code]

• RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-imbalanced Labels for Network Embedding (AAAI'18). [Paper] [Code]

4. Graph Kernels

• Matching Node Embeddings for Graph Similarity (AAAI'17). [Paper] [Code]

• RetGK: Graph Kernels based on Return Probabilities of Random Walks (NIPS'18). [Paper] [Code]

• Anonymous Walk Embeddings (ICML'18). [Paper] [Code]

• Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding (KDD'19). [Paper] [Code]