Fuzzy Logic Based Logical Query Answering on Knowledge Graphs

TL;DR

FuzzQE introduces a fuzzy logic-based framework for logical query answering on knowledge graphs, achieving superior performance without extensive training data, and aligning with classical logic principles.

Contribution

The paper presents a learning-free, fuzzy logic-based approach for FOL query answering on KGs, addressing limitations of previous methods and reducing training data requirements.

Findings

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

FuzzQE trained only on KG link prediction data achieves comparable results.

FuzzQE adheres to classical logic principles in its logical operators.

Abstract

Answering complex First-Order Logical (FOL) queries on large-scale incomplete knowledge graphs (KGs) is an important yet challenging task. Recent advances embed logical queries and KG entities in the same space and conduct query answering via dense similarity search. However, most logical operators designed in previous studies do not satisfy the axiomatic system of classical logic, limiting their performance. Moreover, these logical operators are parameterized and thus require many complex FOL queries as training data, which are often arduous to collect or even inaccessible in most real-world KGs. We thus present FuzzQE, a fuzzy logic based logical query embedding framework for answering FOL queries over KGs. FuzzQE follows fuzzy logic to define logical operators in a principled and learning-free manner, where only entity and relation embeddings require learning. FuzzQE can further benefit from labeled complex logical queries for training. Extensive experiments on two benchmark datasets demonstrate that FuzzQE provides significantly better performance in answering FOL queries compared to state-of-the-art methods. In addition, FuzzQE trained with only KG link prediction can achieve comparable performance to those trained with extra complex query data.