Link Prediction
808 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
Hierarchical Attention Models for Multi-Relational Graphs
BR-GCN models use bi-level attention to learn node embeddings through (1) node-level attention, and (2) relation-level attention.
Mitigating Heterogeneity among Factor Tensors via Lie Group Manifolds for Tensor Decomposition Based Temporal Knowledge Graph Embedding
dellixx/tkbc-lie
•
•
Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task.
GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection
facebookresearch/glemos
•
•
NeurIPS 2023
The choice of a graph learning (GL) model (i. e., a GL algorithm and its hyperparameter settings) has a significant impact on the performance of downstream tasks.
MPXGAT: An Attention based Deep Learning Model for Multiplex Graphs Embedding
marcob46/mpxgat
•
•
Graph representation learning has rapidly emerged as a pivotal field of study.
Diffusion-based Negative Sampling on Graphs for Link Prediction
ntkien1904/dmns
•
•
Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space.
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
tmlr-group/one-shot-subgraph
•
•
To deduce new facts on a knowledge graph (KG), a link predictor learns from the graph structure and collects local evidence to find the answer to a given query.
RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion
Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks.
Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling
cods-gcs/kgtosa
•
•
We refer to this subgraph as a task-oriented subgraph (TOSG), which contains a subset of task-related node and edge types in G. Training the task using TOSG instead of G alleviates the excessive computation required for a large KG.
Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
wondergo2017/sild
•
•
NeurIPS 2023
In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.
Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models
Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links.
