Link Prediction
811 papers with code • 78 benchmarks • 63 datasets
Link Prediction is a task in graph and network analysis where the goal is to predict missing or future connections between nodes in a network. Given a partially observed network, the goal of link prediction is to infer which links are most likely to be added or missing based on the observed connections and the structure of the network.
( Image credit: Inductive Representation Learning on Large Graphs )
Benchmarks
These leaderboards are used to track progress in Link Prediction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Link Prediction models and implementations
IMDb Movie Reviews
MovieLens
Pubmed
OGB
FB15k
Cora
YAGO
Subtasks
Latest papers
OpenGraph: Towards Open Graph Foundation Models
hkuds/opengraph
•
•
By effectively capturing the graph's underlying structure, these GNNs have shown great potential in enhancing performance in graph learning tasks, such as link prediction and node classification.
SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding
Our framework offers a simple but comprehensive way to understand the underlying patterns and trends in dynamic KG, thereby enhancing the accuracy of predictions and the relevance of recommendations.
Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
sumsky21/unlink-to-unlearn
•
•
As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia.
Multi-Label Zero-Shot Product Attribute-Value Extraction
We propose HyperPAVE, a multi-label zero-shot attribute value extraction model that leverages inductive inference in heterogeneous hypergraphs.
Hierarchical Position Embedding of Graphs with Landmarks and Clustering for Link Prediction
kmswin1/hplc
•
•
HPLC leverages the positional information of nodes based on landmarks at various levels of hierarchy such as nodes' distances to landmarks, inter-landmark distances and hierarchical grouping of clusters.
NetInfoF Framework: Measuring and Exploiting Network Usable Information
amazon-science/network-usable-info-framework
•
•
Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well?
Link-aware link prediction over temporal graph by pattern recognition
lbq8942/tgacn
•
•
A temporal graph can be considered as a stream of links, each of which represents an interaction between two nodes at a certain time.
Dynamic Graph Information Bottleneck
ringbdstack/dgib
•
•
Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy the Minimal-Sufficient-Consensual (MSC) Condition.
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
shamim-hussain/egt_pytorch
•
•
We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
Masked Graph Autoencoder with Non-discrete Bandwidths
newiz430/bandana
•
•
Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution.
