Link Prediction
806 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 with no code
CORE: Data Augmentation for Link Prediction via Information Bottleneck
Link prediction (LP) is a fundamental task in graph representation learning, with numerous applications in diverse domains.
Binder: Hierarchical Concept Representation through Order Embedding of Binary Vectors
Hyperbolic embedding improves embedding quality by exploiting the ever-expanding property of Hyperbolic space, but it also suffers from the same fate as box embedding as gradient descent like optimization is not simple in the Hyperbolic space.
Progressive Knowledge Graph Completion
In this paper, we investigate three crucial processes relevant to real-world construction scenarios: (a) the verification process, which arises from the necessity and limitations of human verifiers; (b) the mining process, which identifies the most promising candidates for verification; and (c) the training process, which harnesses verified data for subsequent utilization; in order to achieve a transition toward more realistic challenges.
Fair Graph Neural Network with Supervised Contrastive Regularization
In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation.
Generative-Contrastive Heterogeneous Graph Neural Network
In recent years, inspired by self-supervised learning, contrastive Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential by utilizing data augmentation and discriminators for downstream tasks.
Novel Node Category Detection Under Subpopulation Shift
We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel categories in attributed graphs under subpopulation shifts.
HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs
To address this issue, we propose a Multi-Level Embedding framework of nodes on a heterogeneous graph (HeteroMILE) - a generic methodology that allows contemporary graph embedding methods to scale to large graphs.
Instruction-based Hypergraph Pretraining
However, the gap between training objectives and the discrepancy between data distributions in pretraining and downstream tasks hinders the transfer of the pretrained knowledge.
Directed Criteria Citation Recommendation and Ranking Through Link Prediction
We explore link prediction as a proxy for automatically surfacing documents from existing literature that might be topically or contextually relevant to a new document.
Multi-Relational Graph Neural Network for Out-of-Domain Link Prediction
Dynamic multi-relational graphs are an expressive relational representation for data enclosing entities and relations of different types, and where relationships are allowed to vary in time.
