Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs

TL;DR

This paper introduces a novel Query Instruction Parsing Plugin (QIPP) that leverages pre-trained language models and code-like instructions to improve logical query understanding in knowledge graph embedding, enhancing model performance.

Contribution

The paper proposes a new QIPP framework using code-like instructions and PLMs to better capture query patterns, addressing pattern-entity alignment bias in KGQE models.

Findings

Improves performance of eight KGQE models

Outperforms two state-of-the-art QPL methods

Enhances logical query understanding in knowledge graphs

Abstract

Knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. To enhance the generalization of KGQE models, recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. The whole process is commonly referred to as Query Pattern Learning (QPL). However, current QPL methods typically suffer from the pattern-entity alignment bias problem, leading to the learned defective query patterns limiting KGQE models' performance. To address this problem, we propose an effective Query Instruction Parsing Plugin (QIPP) that leverages the context awareness of Pre-trained Language Models (PLMs) to capture latent query patterns from code-like query instructions. Unlike the external information introduced by previous QPL methods, we first propose code-like instructions to express FOL queries in an alternative format. This format utilizes textual variables and nested tuples to convey the logical semantics within FOL queries, serving as raw materials for a PLM-based instruction encoder to obtain complete query patterns. Building on this, we design a query-guided instruction decoder to adapt query patterns to KGQE models. To further enhance QIPP's effectiveness across various KGQE models, we propose a query pattern injection mechanism based on compressed optimization boundaries and an adaptive normalization component, allowing KGQE models to utilize query patterns more efficiently. Extensive experiments demonstrate that our plug-and-play method improves the performance of eight basic KGQE models and outperforms two state-of-the-art QPL methods.