Progressive Knowledge Graph Completion

TL;DR

This paper introduces the Progressive Knowledge Graph Completion (PKGC) task, which models real-world KG completion by integrating verification, mining, and training processes, and proposes modules to accelerate this process.

Contribution

It presents the PKGC task that better reflects real-world KG completion challenges and introduces two modules to improve processing efficiency.

Findings

Performance in link prediction does not correlate well with PKGC.

The proposed modules significantly speed up the mining process.

Deeper analysis reveals key factors affecting PKGC results.

Abstract

Knowledge Graph Completion (KGC) has emerged as a promising solution to address the issue of incompleteness within Knowledge Graphs (KGs). Traditional KGC research primarily centers on triple classification and link prediction. Nevertheless, we contend that these tasks do not align well with real-world scenarios and merely serve as surrogate benchmarks. In this paper, we investigate three crucial processes relevant to real-world construction scenarios: (a) the verification process, which arises from the necessity and limitations of human verifiers; (b) the mining process, which identifies the most promising candidates for verification; and (c) the training process, which harnesses verified data for subsequent utilization; in order to achieve a transition toward more realistic challenges. By integrating these three processes, we introduce the Progressive Knowledge Graph Completion (PKGC) task, which simulates the gradual completion of KGs in real-world scenarios. Furthermore, to expedite PKGC processing, we propose two acceleration modules: Optimized Top-$k$ algorithm and Semantic Validity Filter. These modules significantly enhance the efficiency of the mining procedure. Our experiments demonstrate that performance in link prediction does not accurately reflect performance in PKGC. A more in-depth analysis reveals the key factors influencing the results and provides potential directions for future research.