English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Many systems have been developed in recent years to mine logical rules fromlarge-scale Knowledge Graphs (KGs), on the grounds that representingregularities as rules enables both the interpretable inference of new facts,and the explanation of known facts. Among these systems, the walk-based methodsthat generate the instantiated rules containing constants by abstractingsampled paths in KGs demonstrate strong predictive performance andexpressivity. However, due to the large volume of possible rules, these systemsdo not scale well where computational resources are often wasted on generatingand evaluating unpromising rules. In this work, we address such scalabilityissues by proposing new methods for pruning unpromising rules using rulehierarchies. The approach consists of two phases. Firstly, since rulehierarchies are not readily available in walk-based methods, we have built aRule Hierarchy Framework (RHF), which leverages a collection of subsumptionframeworks to build a proper rule hierarchy from a set of learned rules. Andsecondly, we adapt RHF to an existing rule learner where we design andimplement two methods for Hierarchical Pruning (HPMs), which utilize thegenerated hierarchies to remove irrelevant and redundant rules. Throughexperiments over four public benchmark datasets, we show that the applicationof HPMs is effective in removing unpromising rules, which leads to significantreductions in the runtime as well as in the number of learned rules, withoutcompromising the predictive performance.

Building Rule Hierarchies for Efficient Logical Rule Learning from Knowledge Graphs