Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

10/22/2020
by   Hongyu Ren, et al.
23

One of the fundamental problems in Artificial Intelligence is to perform complex multi-hop logical reasoning over the facts captured by a knowledge graph (KG). This problem is challenging, because KGs can be massive and incomplete. Recent approaches embed KG entities in a low dimensional space and then use these embeddings to find the answer entities. However, it has been an outstanding challenge of how to handle arbitrary first-order logic (FOL) queries as present methods are limited to only a subset of FOL operators. In particular, the negation operator is not supported. An additional limitation of present methods is also that they cannot naturally model uncertainty. Here, we present BetaE, a probabilistic embedding framework for answering arbitrary FOL queries over KGs. BetaE is the first method that can handle a complete set of first-order logical operations: conjunction (∧), disjunction (∨), and negation (). 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. Logical operations are performed in the embedding space by neural operators over the probabilistic embeddings. We demonstrate the performance of BetaE on answering arbitrary FOL queries on three large, incomplete KGs. While being more general, BetaE also increases relative performance by up to 25.4 reasoning methods that can only handle conjunctive queries without negation.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/27/2022

Query2Particles: Knowledge Graph Reasoning with Particle Embeddings

Answering complex logical queries on incomplete knowledge graphs (KGs) w...
05/02/2022

Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly ch...
06/05/2018

Querying Complex Networks in Vector Space

Learning vector embeddings of complex networks is a powerful approach us...
05/23/2022

FLEX: Feature-Logic Embedding Framework for CompleX Knowledge Graph Reasoning

Current best performing models for knowledge graph reasoning (KGR) are b...
10/26/2021

Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs

Logical reasoning over Knowledge Graphs (KGs) is a fundamental technique...
12/23/2020

Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs

Knowledge Graphs (KGs) are ubiquitous structures for information storage...
02/28/2021

Logic Embeddings for Complex Query Answering

Answering logical queries over incomplete knowledge bases is challenging...

Code Repositories