Graph Representation Learning
284 papers with code • 1 benchmarks • 4 datasets
The goal of Graph Representation Learning is to construct a set of features (‘embeddings’) representing the structure of the graph and the data thereon. We can distinguish among Node-wise embeddings, representing each node of the graph, Edge-wise embeddings, representing each edge in the graph, and Graph-wise embeddings representing the graph as a whole.
Benchmarks
These leaderboards are used to track progress in Graph Representation Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Graph Representation Learning models and implementations
IMDB-BINARY
COMA
WikiGraphs
Most implemented papers
How Powerful are Graph Neural Networks?
weihua916/powerful-gnns
•
•
ICLR 2019
Here, we present a theoretical framework for analyzing the expressive power of GNNs to capture different graph structures.
Hierarchical Graph Representation Learning with Differentiable Pooling
dmlc/dgl
•
•
NeurIPS 2018
Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction.
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
IBM/EvolveGCN
•
•
Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.
GraphSAINT: Graph Sampling Based Inductive Learning Method
GraphSAINT/GraphSAINT
•
•
ICLR 2020
Graph Convolutional Networks (GCNs) are powerful models for learning representations of attributed graphs.
GraphGAN: Graph Representation Learning with Generative Adversarial Nets
The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space.
Fast Graph Representation Learning with PyTorch Geometric
We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch.
A Fair Comparison of Graph Neural Networks for Graph Classification
diningphil/gnn-comparison
•
•
ICLR 2020
We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.
Understanding Negative Sampling in Graph Representation Learning
zyang-16/MCNS
•
•
To the best of our knowledge, we are the first to derive the theory and quantify that the negative sampling distribution should be positively but sub-linearly correlated to their positive sampling distribution.
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
THUDM/GCC
•
•
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
michiyasunaga/qagnn
•
•
NAACL 2021
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG.
