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

TL;DR

FLEX is a novel knowledge graph reasoning framework that effectively handles all first-order logic operations and supports various feature spaces, significantly outperforming existing methods.

Contribution

Introducing FLEX, the first KGR framework capable of true FOL operation handling and flexible feature space support, overcoming limitations of prior geometry-based models.

Findings

FLEX outperforms state-of-the-art methods on benchmark datasets.

FLEX can handle all FOL operations including conjunction, disjunction, and negation.

Supports various feature spaces beyond traditional geometric constraints.

Abstract

Current best performing models for knowledge graph reasoning (KGR) introduce geometry objects or probabilistic distributions to embed entities and first-order logical (FOL) queries into low-dimensional vector spaces. They can be summarized as a center-size framework (point/box/cone, Beta/Gaussian distribution, etc.). However, they have limited logical reasoning ability. And it is difficult to generalize to various features, because the center and size are one-to-one constrained, unable to have multiple centers or sizes. To address these challenges, we instead propose a novel KGR framework named Feature-Logic Embedding framework, FLEX, which is the first KGR framework that can not only TRULY handle all FOL operations including conjunction, disjunction, negation and so on, but also support various feature spaces. Specifically, the logic part of feature-logic framework is based on vector logic, which naturally models all FOL operations. Experiments demonstrate that FLEX significantly outperforms existing state-of-the-art methods on benchmark datasets.