Graph Embedding

474 papers with code • 1 benchmarks • 11 datasets

Graph embeddings learn a mapping from a network to a vector space, while preserving relevant network properties.

( Image credit: GAT )

Libraries

Use these libraries to find Graph Embedding models and implementations

Most implemented papers

Graph Attention Networks

PetarV-/GAT ICLR 2018

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

DeepGraphLearning/KnowledgeGraphEmbedding ICLR 2019

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links.

Poincaré Embeddings for Learning Hierarchical Representations

facebookresearch/poincare-embeddings NeurIPS 2017

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs.

Inductive Relation Prediction by Subgraph Reasoning

kkteru/grail ICML 2020

The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i. e., embeddings) of entities and relations.

Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction

MIRALab-USTC/KGE-HAKE 21 Nov 2019

HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy.

LINE: Large-scale Information Network Embedding

tangjianpku/LINE 12 Mar 2015

This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction.

Learning Combinatorial Optimization Algorithms over Graphs

Hanjun-Dai/graph_comb_opt NeurIPS 2017

The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error.

GraphSAINT: Graph Sampling Based Inductive Learning Method

GraphSAINT/GraphSAINT ICLR 2020

Graph Convolutional Networks (GCNs) are powerful models for learning representations of attributed graphs.

graph2vec: Learning Distributed Representations of Graphs

benedekrozemberczki/karateclub 17 Jul 2017

Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs.

NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding

yzhangee/NSCaching 16 Dec 2018

Negative sampling, which samples negative triplets from non-observed ones in the training data, is an important step in KG embedding.