graph-representation-learning

Knowledge Graph Embedding

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-representation-learning

Trend

Dataset

Best Model

Actions

FB15k

Libraries

i

Use these libraries to find graph-representation-learning models and implementations

pykeen/pykeen

3 papers 1,503

Datasets

FB15k

KG20C

KGRC-RDF-star

GEval for KGRC-RDF-star

Subtasks

Open Knowledge Graph Embedding

Most implemented papers

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Zhiqing Sun, Jian-Yun Nie, Jian Tang, Zhihong Deng•Wed Sep 26 2018

Experimental results show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.

2550

Content

nicolas-hbt/versatile-embeddings

3 papers 15

Accenture/AmpliGraph

2 papers 2,079

dice-group/dice-embeddings

2 papers 35

0

Paper Graph

Inductive Relation Prediction by Subgraph Reasoning

William L. Hamilton, Komal K. Teru, E. Denis•Fri Nov 15 2019

A graph neural network based relation prediction framework, GraIL, that reasons over local subgraph structures and has a strong inductive bias to learn entity-independent relational semantics is proposed.

468 0

Paper Graph

Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction

Yongdong Zhang, Zhanqiu Zhang, Jie Wang, Jianyu Cai•Wed Nov 20 2019

A novel knowledge graph embedding model, Hierarchy-Aware Knowledge Graph Embedding (HAKE), which maps entities into the polar coordinate system and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.

452 0

Paper Graph

NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding

Quanming Yao, Yingxia Shao, Yongqi Zhang, Lei Chen•Sat Dec 15 2018

The extensive experiments show that the directly keeping track of negative triplets with large scores with cache can gain significant improvement on various KG embedding models, and outperform the state-of-the-arts negative sampling methods based on GAN.

135 0

Paper Graph

Knowledge Graph Embedding for Ecotoxicological Effect Prediction

Jiaoyan Chen, Ernesto Jiménez-Ruiz, E. B. Myklebust, Raoul Wolf, K. Tollefsen•Mon Jul 01 2019

This paper explores the suitability of using a knowledge graph embedding approach for ecotoxicological effect prediction, and results show that the knowledge graph based approach improves the selected baselines.

25 0

Paper Graph

Composition-based Multi-Relational Graph Convolutional Networks

P. Talukdar, Shikhar Vashishth, Soumya Sanyal, Vikram Nitin•Thu Nov 07 2019

This paper proposes CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph and leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations.

1045 0

Paper Graph

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

Quanming Yao, Yongqi Zhang, Lei Chen•Sun Oct 25 2020

This work defines the Interstellar as a recurrent neural architecture search problem for the short-term and long-term information along the relational paths, and proposes to search for recurrent architecture as the Interstellar for different KG tasks.

22 0

Paper Graph

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

William Yang Wang, Liwei Cai•Fri Nov 10 2017

Inspired by generative adversarial networks (GANs), this framework uses one knowledge graph embedding model as a negative sample generator to assist the training of the desired model, which acts as the discriminator in GANs.

301 0

Paper Graph

MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction

A. Takasu, Hung-Nghiep Tran•Thu Jun 30 2022

The Multi-partition Embedding Interaction iMproved beyond block term format (MEIM) model is introduced, with independent core tensor for ensemble effects and soft orthogonality for max-rank mapping, in addition to multi-partitions embedding.

20 0

Paper Graph

Adding a benchmark result helps the community track progress.