Link Prediction
Link prediction is a task to estimate the probability of links between nodes in a graph.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Subtasks
Greatest papers with code
PyTorch-BigGraph: A Large-scale Graph Embedding System
• facebookresearch/PyTorch-BigGraph
• 
Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks.
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
• facebookresearch/PyTorch-BigGraph
•
We consider learning representations of entities and relations in KBs using the neural-embedding approach.
#7 best model for
Link Prediction
on WN18
Inductive Representation Learning on Large Graphs
NeurIPS 2017
• williamleif/GraphSAGE
• 
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.
Graph Attention Networks
ICLR 2018
• PetarV-/GAT
•
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.
#3 best model for
Document Classification
on Cora
DOCUMENT CLASSIFICATION GRAPH EMBEDDING LINK PREDICTION NODE CLASSIFICATION
Graph Convolutional Matrix Completion
• tkipf/gae
•
We consider matrix completion for recommender systems from the point of view of link prediction on graphs.
Modeling Relational Data with Graph Convolutional Networks
• tkipf/gae
•
We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification.
INFORMATION RETRIEVAL KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPHS LINK PREDICTION
Variational Graph Auto-Encoders
• tkipf/gae
•
We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE).
SOTA for Link Prediction on Pubmed
LINE: Large-scale Information Network Embedding
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.
#5 best model for
Node Classification
on Wikipedia
GRAPH EMBEDDING LINK PREDICTION NETWORK EMBEDDING NODE CLASSIFICATION
Higher-Order Factorization Machines
Factorization machines (FMs) are a supervised learning approach that can use second-order feature combinations even when the data is very high-dimensional.
Convolutional 2D Knowledge Graph Embeddings
In this work, we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets.
SOTA for Link Prediction on WN18