Graph Pattern-based Association Rules Evaluated Under No-repeated-anything Semantics in the Graph Transactional Setting

TL;DR

This paper introduces graph pattern-based association rules for directed labeled multigraphs, enabling more effective graph analysis under no-repeated-anything semantics with probabilistic evaluation metrics.

Contribution

It presents a novel formalism for GPARs that extends existing graph rule frameworks and analyzes their probabilistic properties and relations to classical metrics.

Findings

GPARs support both generative and evaluative tasks.

Metrics like confidence and lift are adapted to a probabilistic graph setting.

Conditions are identified under which these metrics preserve classical properties.

Abstract

We introduce graph pattern-based association rules (GPARs) for directed labeled multigraphs such as RDF graphs. GPARs support both generative tasks, where a graph is extended, and evaluative tasks, where the plausibility of a graph is assessed. The framework goes beyond related formalisms such as graph functional dependencies, graph entity dependencies, relational association rules, graph association rules, multi-relation and path association rules, and Horn rules. Given a collection of graphs, we evaluate graph patterns under no-repeated-anything semantics, which allows the topology of a graph to be taken into account more effectively. We define a probability space and derive confidence, lift, leverage, and conviction in a probabilistic setting. We further analyze how these metrics relate to their classical itemset-based counterparts and identify conditions under which their characteristic properties are preserved.