Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912457100886016 |
|---|---|
| author | Mukherjee, Kunal Harrison, Zachary Balaneshin, Saeid |
| author_facet | Mukherjee, Kunal Harrison, Zachary Balaneshin, Saeid |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18001 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendations Mukherjee, Kunal Harrison, Zachary Balaneshin, Saeid Information Retrieval Machine Learning Social and Information Networks I.2; I.5 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. |
| title | Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendations |
| topic | Information Retrieval Machine Learning Social and Information Networks I.2; I.5 |
| url | https://arxiv.org/abs/2503.18001 |