Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendations
This work addresses the need for transparency in real estate recommendations to enhance customer confidence, though it is incremental as it builds on existing GNN explainability methods.
The paper tackles the lack of explanation techniques for link prediction tasks in graph neural network (GNN)-based recommendation systems by introducing Z-REx, a framework that uses structural and attribute perturbation to generate human-interpretable explanations, resulting in a 61% improvement in Fidelity over state-of-the-art methods.
Transparency and interpretability are crucial for enhancing customer confidence and user engagement, especially when dealing with black-box Machine Learning (ML)-based recommendation systems. Modern recommendation systems leverage Graph Neural Network (GNN) due to their ability to produce high-quality recommendations in terms of both relevance and diversity. Therefore, the explainability of GNN is especially important for Link Prediction (LP) tasks since recommending relevant items can be viewed as predicting links between users and items. GNN explainability has been a well-studied field, but existing methods primarily focus on node or graph-level tasks, leaving a gap in LP explanation techniques. This work introduces Z-REx, a GNN explanation framework designed explicitly for heterogeneous link prediction tasks. Z-REx utilizes structural and attribute perturbation to identify critical substructures and important features while reducing the search space by leveraging domain-specific knowledge. In our experimentation, we show the efficacy of Z-REx in generating contextually relevant and human-interpretable explanations for ZiGNN, a GNN-based recommendation engine, using a real-world real-estate dataset from Zillow Group, Inc. We compare against State-of-The-Art (SOTA) GNN explainers to show Z-REx outperforms them by 61% in the Fidelity metric by producing superior human-interpretable explanations.