Rethinking Node Representation Interpretation through Relation Coherence

TL;DR

This paper introduces NCI, a new method for interpreting node representations in graph models by measuring relation coherence, and demonstrates its effectiveness in improving interpretation accuracy and understanding model behavior.

Contribution

The paper proposes NCI, a novel interpretation method for node representations, and introduces IME for evaluating interpretation accuracy, addressing validation gaps in explainable AI for graphs.

Findings

NCI reduces interpretation error by 39% on average.

NCI provides insights into node representations in various graph models.

The method enhances understanding of relation capture in node embeddings.

Abstract

Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research that focuses on interpretation lacks validation, and thus the reliability of such methods is unclear. We address this gap by proposing a novel interpretation method-Node Coherence Rate for Representation Interpretation (NCI)-which quantifies how well different node relations are captured in node representations. We also propose a novel method (IME) to evaluate the accuracy of different interpretation methods. Our experimental results demonstrate that NCI reduces the error of the previous best approach by an average of 39%. We then apply NCI to derive insights about the node representations produced by several graph-based methods and assess their quality in unsupervised settings.