About

Link prediction is a task to estimate the probability of links between nodes in a graph.

( Image credit: Inductive Representation Learning on Large Graphs )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Neural Collaborative Filtering vs. Matrix Factorization Revisited

19 May 2020google-research/google-research

This approach is often referred to as neural collaborative filtering (NCF).

LINK PREDICTION

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

KDD 2019 google-research/google-research

Furthermore, Cluster-GCN allows us to train much deeper GCN without much time and memory overhead, which leads to improved prediction accuracy---using a 5-layer Cluster-GCN, we achieve state-of-the-art test F1 score 99. 36 on the PPI dataset, while the previous best result was 98. 71 by [16].

 Ranked #1 on Node Classification on Pubmed (F1 metric)

4 GRAPH CLUSTERING LINK PREDICTION NODE CLASSIFICATION

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

6 May 2019google-research/google-research

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.

GRAPH EMBEDDING LINK PREDICTION

Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

15 Sep 2020dmlc/dgl

Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content.

GRAPH REPRESENTATION LEARNING LINK PREDICTION NODE CLASSIFICATION NODE CLUSTERING

Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs

11 Apr 2019dmlc/dgl

The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp.

KNOWLEDGE GRAPHS LINK PREDICTION

Graph Attention Networks

ICLR 2018 aymericdamien/TopDeepLearning

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.

DOCUMENT CLASSIFICATION GRAPH CLASSIFICATION GRAPH EMBEDDING GRAPH REGRESSION LINK PREDICTION NODE CLASSIFICATION SKELETON BASED ACTION RECOGNITION

Neural Factorization Machines for Sparse Predictive Analytics

16 Aug 2017shenweichen/DeepCTR

However, FM models feature interactions in a linear way, which can be insufficient for capturing the non-linear and complex inherent structure of real-world data.

LINK PREDICTION

PyTorch-BigGraph: A Large-scale Graph Embedding System

28 Mar 2019facebookresearch/PyTorch-BigGraph

Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks.

 Ranked #1 on Link Prediction on YouTube (Macro F1 metric)

GRAPH EMBEDDING GRAPH PARTITIONING LINK PREDICTION

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

20 Dec 2014facebookresearch/PyTorch-BigGraph

We consider learning representations of entities and relations in KBs using the neural-embedding approach.

LINK PREDICTION

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 CLASSIFICATION GRAPH REGRESSION LINK PREDICTION NODE CLASSIFICATION REPRESENTATION LEARNING