Rethinking Node Representation Interpretation through Relation Coherence
This addresses the need for reliable interpretation methods in graph-based AI to uncover biases and build trust, though it is incremental as it builds on prior work in explainable AI.
The paper tackles the problem of interpreting node representations in graph-based models by proposing NCI, a method that quantifies how well node relations are captured, and IME, a method to evaluate interpretation accuracy; it shows that NCI reduces error by an average of 39% compared to previous approaches.
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.