Benchmarks
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
Greatest papers with code
Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks
It is not straightforward to integrate the content of each node in the current state-of-the-art network embedding methods.
MULTI-CLASS CLASSIFICATION NETWORK EMBEDDING NODE CLUSTERING
MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• cynricfu/MAGNN
• 
A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types.
Ranked #1 on
Node Clustering
on IMDb
GRAPH EMBEDDING LINK PREDICTION NODE CLASSIFICATION NODE CLUSTERING
Simple and Effective Graph Autoencoders with One-Hop Linear Models
• deezer/linear_graph_autoencoders
• 
Over the last few years, graph autoencoders (AE) and variational autoencoders (VAE) emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• deezer/linear_graph_autoencoders
•
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
StructPool: Structured Graph Pooling via Conditional Random Fields
ICLR 2020
• Nate1874/StructPool
•
Learning high-level representations for graphs is of great importance for graph analysis tasks.
Heterogeneous Deep Graph Infomax
• YuxiangRen/Heterogeneous-Deep-Graph-Infomax
•
The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering.
Ranked #7 on
Heterogeneous Node Classification
on DBLP (PACT) 14k
CLASSIFICATION GRAPH REPRESENTATION LEARNING HETEROGENEOUS NODE CLASSIFICATION NODE CLUSTERING
RWR-GAE: Random Walk Regularization for Graph Auto Encoders
Node embeddings have become an ubiquitous technique for representing graph data in a low dimensional space.
Ranked #2 on
Graph Clustering
on Cora
Adaptive Graph Encoder for Attributed Graph Embedding
• thunlp/AGE
•
Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.
Simple Spectral Graph Convolution
ICLR 2021
• allenhaozhu/SSGC
•
Our spectral analysis shows that our simple spectral graph convolution used in S^2GC is a low-pass filter which partitions networks into a few large parts.
Ranked #1 on
Node Clustering
on Wiki
Accurate Learning of Graph Representations with Graph Multiset Pooling
Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks.
Ranked #1 on
Graph Classification
on Tox21
GRAPH CLASSIFICATION GRAPH CLUSTERING GRAPH EMBEDDING GRAPH GENERATION GRAPH LEARNING GRAPH RECONSTRUCTION NODE CLUSTERING