Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment

TL;DR

This paper introduces BotGNN, a novel method that integrates multi-relational domain knowledge into Graph Neural Networks using mode-directed inverse entailment, enhancing their performance and representational capacity.

Contribution

The paper presents a new technique, BotGNN, that incorporates background knowledge into GNNs via mode-directed inverse entailment, bridging GNNs and ILP.

Findings

BotGNN outperforms standard GNNs without background knowledge.

BotGNN performs better than propositionalized background knowledge features.

BotGNN compares favorably to ILP with most-specific clauses.

Abstract

We present a general technique for constructing Graph Neural Networks (GNNs) capable of using multi-relational domain knowledge. The technique is based on mode-directed inverse entailment (MDIE) developed in Inductive Logic Programming (ILP). Given a data instance $e$ and background knowledge $B$, MDIE identifies a most-specific logical formula $\bot_B(e)$ that contains all the relational information in $B$ that is related to $e$. We represent $\bot_B(e)$ by a "bottom-graph" that can be converted into a form suitable for GNN implementations. This transformation allows a principled way of incorporating generic background knowledge into GNNs: we use the term `BotGNN' for this form of graph neural networks. For several GNN variants, using real-world datasets with substantial background knowledge, we show that BotGNNs perform significantly better than both GNNs without background knowledge and a recently proposed simplified technique for including domain knowledge into GNNs. We also provide experimental evidence comparing BotGNNs favourably to multi-layer perceptrons (MLPs) that use features representing a "propositionalised" form of the background knowledge; and BotGNNs to a standard ILP based on the use of most-specific clauses. Taken together, these results point to BotGNNs as capable of combining the computational efficacy of GNNs with the representational versatility of ILP.