In recent years, considerable progress has been made on improving the interpretability of machine learning models. This is essential, as complex deep learning models with millions of parameters produce state of the art results, but it can be nearly impossible to explain their predictions. While various explainability techniques have achieved impressive results, nearly all of them assume each data instance to be independent and identically distributed (iid). This excludes relational models, such as Statistical Relational Learning (SRL), and the recently popular Graph Neural Networks (GNNs), resulting in few options to explain them. While there does exist one work on explaining GNNs, GNN-Explainer, they assume access to the gradients of the model to learn explanations, which is restrictive in terms of its applicability across non-differentiable relational models and practicality. In this work, we develop RelEx, a model-agnostic relational explainer to explain black-box relational models with only access to the outputs of the black-box. RelEx is able to explain any relational model, including SRL models and GNNs. We compare RelEx to the state-of-the-art relational explainer, GNN-Explainer, and relational extensions of iid explanation models and show that RelEx achieves comparable or better performance, while remaining model-agnostic.

What you'll be working on You would become a member of the machine learning development team, working on the more mathematically oriented features in our software, written in Java 11, Scala, Kotlin and JRuby. Working closely together with data scientists and domain experts, you'd be writing performant and beautiful code to implement new machine learning algorithms, as well as profiling, optimizing and improving existing ones. You get to work closely with experts both in the field of supply chain and in software engineering. What you'll bring to the table We offer flexible work hours and arrangements, the ability to choose your own tools, smartphone and broadband connection benefits and lots of sporting options. RELEX offers flexible career paths and the possibility to continuously develop your skills, for example by courses, conferences or moving between teams within the organisation according to your interests.