Embedding Uncertain Knowledge Graphs

by   Xuelu Chen, et al.

Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different learning objectives. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results on these tasks, and consistently outperforms baselines on these tasks.


page 1

page 2

page 3

page 4


Knowledge Hypergraphs: Extending Knowledge Graphs Beyond Binary Relations

Knowledge graphs store facts using relations between pairs of entities. ...

On2Vec: Embedding-based Relation Prediction for Ontology Population

Populating ontology graphs represents a long-standing problem for the Se...

Direct Fact Retrieval from Knowledge Graphs without Entity Linking

There has been a surge of interest in utilizing Knowledge Graphs (KGs) f...

Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning

Knowledge bases often consist of facts which are harvested from a variet...

Computing and Maintaining Provenance of Query Result Probabilities in Uncertain Knowledge Graphs

Knowledge graphs (KG) that model the relationships between entities as l...

RelSifter: Scoring Triples from Type-like Relations - The Samphire Triple Scorer at WSDM Cup 2017

We present RelSifter, a supervised learning approach to the problem of a...

Exploring the Challenges towards Lifelong Fact Learning

So far life-long learning (LLL) has been studied in relatively small-sca...

Please sign up or login with your details

Forgot password? Click here to reset