knowledge-graph-completion

Knowledge Graphs

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 knowledge-graph-completion

Trend

Dataset

Best Model

Actions

MARS (Multimodal Analogical Reasoning dataSet)

WikiKG90M-LSC

Libraries

i

Use these libraries to find knowledge-graph-completion models and implementations

Accenture/AmpliGraph

4 papers 2,079

Datasets

Subtasks

Knowledge Graph Completion Complex Query Answering Open Knowledge Graph Canonicalization Relational Pattern Learning Relational Pattern Learning

Most implemented papers

Modeling Relational Data with Graph Convolutional Networks

M. Welling, Rianne van den Berg, Ivan Titov, Thomas Kipf, M. Schlichtkrull, Peter Bloem•Thu Mar 16 2017

It is shown that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

5621

Content

FB15k

alibaba/EasyNLP

3 papers 1,935

bi-graph/emgraph

3 papers 37

Sujit-O/pykg2vec

2 papers 588

faceonlive/ai-research

2 papers 102

MetaQA

DBP15K

ComplexWebQuestions

Jericho

Person-Centric Knowledge Graphs

0

Paper Graph

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Weihua Hu, Matthias Fey, M. Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, J. Leskovec•Fri May 01 2020

The OGB datasets are large-scale, encompass multiple important graph ML tasks, and cover a diverse range of domains, ranging from social and information networks to biological networks, molecular graphs, source code ASTs, and knowledge graphs, indicating fruitful opportunities for future research.

3156 0

Paper Graph

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 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

Convolutional 2D Knowledge Graph Embeddings

Pontus Stenetorp, Sebastian Riedel, Pasquale Minervini, Tim Dettmers•Tue Jul 04 2017

ConvE, a multi-layer convolutional network model for link prediction, is introduced, and it is found that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.

2936 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

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

Hongyu Ren, J. Leskovec•Wed Oct 21 2020

BetaE is the first method that can handle a complete set of first-order logical operations: conjunction, disjunction, and negation, and a key insight of BetaE is to use probabilistic distributions with bounded support, specifically the Beta distribution, and embed queries/entities as distributions, which as a consequence allows us to also faithfully model uncertainty.

240 0

Paper Graph

KGAT: Knowledge Graph Attention Network for Recommendation

Xiangnan He, Tat-Seng Chua, Yixin Cao, Xiang Wang, Meng Liu•Sun May 19 2019

This work proposes a new method named Knowledge Graph Attention Network (KGAT), which explicitly models the high-order connectivities in KG in an end-to-end fashion and significantly outperforms state-of-the-art methods like Neural FM and RippleNet.

2115 0

Paper Graph

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

Weihua Hu, Matthias Fey, Yuxiao Dong, Hongyu Ren, J. Leskovec, Maho Nakata•Tue Mar 16 2021

It is shown that expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.

455 0

Paper Graph

Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings

Weihua Hu, Hongyu Ren, J. Leskovec•Thu Feb 13 2020

Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities as well as the query into a vector space such that entities that answer the query are embedded close to the query. However, prior work models queries as single points in the vector space, which is problematic because a complex query represents a potentially large set of its answer entities, but it is unclear how such a set can be represented as a single point. Furthermore, prior work can only handle queries that use conjunctions ($\wedge$) and existential quantifiers ($\exists$). Handling queries with logical disjunctions ($\vee$) remains an open problem. Here we propose query2box, an embedding-based framework for reasoning over arbitrary queries with $\wedge$, $\vee$, and $\exists$ operators in massive and incomplete KGs. Our main insight is that queries can be embedded as boxes (i.e., hyper-rectangles), where a set of points inside the box corresponds to a set of answer entities of the query. We show that conjunctions can be naturally represented as intersections of boxes and also prove a negative result that handling disjunctions would require embedding with dimension proportional to the number of KG entities. However, we show that by transforming queries into a Disjunctive Normal Form, query2box is capable of handling arbitrary logical queries with $\wedge$, $\vee$, $\exists$ in a scalable manner. We demonstrate the effectiveness of query2box on two large KGs and show that query2box achieves up to 25% relative improvement over the state of the art.

348 0

Paper Graph

Adding a benchmark result helps the community track progress.