RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools

TL;DR

This paper introduces RuDaS, a tool for generating synthetic datasets and evaluation tools to improve rule learning systems in knowledge graphs, addressing current limitations in dataset diversity and evaluation methods.

Contribution

It provides a novel dataset generation tool and evaluation framework for rule learning, filling gaps in existing datasets and assessment approaches.

Findings

Generated diverse datasets covering various rule dependencies

Proposed new performance measures for rule learning evaluation

Facilitated testing of scalability in rule learning systems

Abstract

Logical rules are a popular knowledge representation language in many domains, representing background knowledge and encoding information that can be derived from given facts in a compact form. However, rule formulation is a complex process that requires deep domain expertise,and is further challenged by today's often large, heterogeneous, and incomplete knowledge graphs. Several approaches for learning rules automatically, given a set of input example facts,have been proposed over time, including, more recently, neural systems. Yet, the area is missing adequate datasets and evaluation approaches: existing datasets often resemble toy examples that neither cover the various kinds of dependencies between rules nor allow for testing scalability. We present a tool for generating different kinds of datasets and for evaluating rule learning systems, including new performance measures.