/network-embedding-reading_group

network embedding reading_group

Awesome-network-embedding

Also called network representation learning, graph embedding, knowledge embedding, etc.

The task is to learn the representations of the vertices from a given network.

Survey

Graph Embedding Techniques, Applications, and Performance: A Survey

[arxiv]

Representation Learning on Graphs: Methods and Applications

[arxiv]

Summary of paper about learning node representations of networks

Lapalcian Eigenmap

Graph Factorization

Neural word embedding: Word2Vec

**LINE, DeepWalk, Node2Vec

Multi-view Network Embedding used for multigraph regularization

Learning Distributed Node Representations for Networks with Multiple Views, CIKM'17

Networks with node attributes

--Networks with text information

Network representation learning with reich text information IJCAI'15

--Networks with attributes

Attributed social network embedding arXiv'17

--Variational graph autoencoders

Variational Graph Auto-encoders NIPS Workshop 16

Heterogeneous networks

--Heterogeneous Network Embedding via Deep Architectures

Heterogeneous Network Embedding via Deep Architectures KDD'15

--Heterogeneous Star Network Embedding

Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification WSDM'17

Task-specific network embedding

--Semi-supervised Text Representation

PTE: Predictive Tesxt Embedding through Large-scale Heterogeneous Text Network KDD'15

--Semi-supervised Classification with Graph Convolutional Networks

Semi-supervised Classification with Graph Convolutional Networks ICLR'17

Leverage global structural inforation

GraphRep: Learning graph representation with global structural information CIKM'15

Non-linear methods based on autoencoder

Structural deep network embedding KDD'16

Directed network embedding

Asymmetric transitivity preserving graph embedding KDD'16

Signed network embedding

Signed netowrk embedding in social media SDM'17

Summary of paper about learning representations of Entire networks

Graph Kernels

End-to-end method

--Matrix-based: represent graph as matrice -- affinity matrix

sensitive to node permutations

isomorphic graphs can b maped to differnet matrices

how to find a good intermediate matrix

PATCHY-SAN: Learning Convolutional Neural Networks for Graphs ICML'16

DeepGraph: DeepGraph: Graph Structure Predicts Network Growth

--Sequence-based

DeepCas: an End-to-end Predictor of Information Cascades WWW'17

--Graphical model based: construct graohical model for graphs

Structure2vec: Discriminative Embeddings of Latent Variable Models for Structured Data

Paper References with the implementation(s)

StarSpace

StarSpace: Embed All The Things!, arxiv'17

[code]

ComE

Learning Community Embedding with Community Detection and Node Embedding on Graphs, CIKM'17

[Python]

GraphSAGE

Inductive Representation Learning on Large Graphs, NIPS'17

[arxiv] [Python]

ICE

ICE: Item Concept Embedding via Textual Information, SIGIR'17

[demo] [code]

struc2vec

struc2vec: Learning Node Representations from Structural Identity, KDD'17

[arxiv] [Python]

metapath2vec

metapath2vec: Scalable Representation Learning for Heterogeneous Networks, KDD'17

[paper] [project website]

GCN

Semi-Supervised Classification with Graph Convolutional Networks, ICLR'17

[arxiv] [Python Tensorflow]

GAE

Variational Graph Auto-Encoders, arxiv

[arxiv] [Python Tensorflow]

CANE

CANE: Context-Aware Network Embedding for Relation Modeling, ACL'17

[paper] [Python]

TransNet

TransNet: Translation-Based Network Representation Learning for Social Relation Extraction, IJCAI'17

[Python Tensorflow]

ConvE

Convolutional 2D Knowledge Graph Embeddings, arxiv

[source]

node2vec

node2vec: Scalable Feature Learning for Networks, KDD'16

[arxiv] [Python] [Python-2]

DNGR

Deep Neural Networks for Learning Graph Representations, AAAI'16

[Matlab] [Python Keras]

HolE

Holographic Embeddings of Knowledge Graphs, AAAI'16

[Python-sklearn] [Python-sklearn2]

ComplEx

Complex Embeddings for Simple Link Prediction, ICML'16

[arxiv] [Python]

MMDW

Max-Margin DeepWalk: Discriminative Learning of Network Representation, IJCAI'16

[paper] [Java]

planetoid

Revisiting Semi-supervised Learning with Graph Embeddings, ICML'16

[arxiv] [Python]

PowerWalk

PowerWalk: Scalable Personalized PageRank via Random Walks with Vertex-Centric Decomposition, CIKM'16

[code]

LINE

LINE: Large-scale information network embedding, WWW'15

[arxiv] [C++]

PTE

PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks, KDD'15

[C++]

GraRep

Grarep: Learning graph representations with global structural information, CIKM'15

[Matlab]

KB2E

Learning Entity and Relation Embeddings for Knowledge Graph Completion, AAAI'15

[paper] [C++] [faster version]

TADW

Network Representation Learning with Rich Text Information, IJCAI'15

[paper] [Matlab]

DeepWalk

DeepWalk: Online Learning of Social Representations, KDD'14

[arxiv] [Python]

GEM

Graph Embedding Techniques, Applications, and Performance: A Survey

[arxiv] [MIX]

Paper References

CONE, CONE: Community Oriented Network Embedding, arxiv'17

LANE, Label Informed Attributed Network Embedding, WSDM'17

Graph2Gauss, Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking, arxiv [Bonus Animation]

Scalable Graph Embedding for Asymmetric Proximity, AAAI'17

Structural Deep Network Embedding, KDD'16

Query-based Music Recommendations via Preference Embedding, RecSys'16

Tri-party deep network representation, IJCAI'16

Heterogeneous Network Embedding via Deep Architectures, KDD'15

Neural Word Embedding As Implicit Matrix Factorization, NIPS'14

Distributed large-scale natural graph factorization, WWW'13

From Node Embedding To Community Embedding, arxiv

Walklets: Multiscale Graph Embeddings for Interpretable Network Classification, arxiv

Comprehend DeepWalk as Matrix Factorization, arxiv

Related List

Must-read papers on NRL/NE.

Network Embedding Resources

awesome-embedding-models

2vec-type embedding models

Related Project

Stanford Network Analysis Project website

proNet-core github

To do

use task supervision loss for vision task

--completely replace the reconstruction loss computed using the decoder

Inductive representation learning on large graph

Semi-supervised classification with graph convolutional network

--or included along the the decoder loss

Revisiting semi-supervised learning with graph embeddings