{"ID":3004893,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T11:10:57.854545281Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03495","arxiv_id":"2606.03495","title":"HiSE: A Lightweight Hierarchical Semantic Explainer for Heterogeneous Graph Neural Networks","abstract":"Heterogeneous graph neural networks (HGNNs) have demonstrated remarkable performance in modeling complex relational data, however their interpretability in high-stakes applications remains a critical challenge. Existing explanation methods suffer from two major limitations: on the one hand, the generated explanations fail to reflect the inherent semantic hierarchy of HGNNs, resulting in a lack of fidelity to the model's internal decision-making mechanism; on the other hand, feature explanations often rely on complex search or perturbation mechanisms, leading to excessive computational complexity and poor efficiency. To address these issues, we propose HiSE, a lightweight feature-oriented interpretable model for HGNNs. HiSE achieves semantically aware feature explanations through hierarchical semantic modeling: at the semantic level, local surrogate models based on the Least Absolute Shrinkage and Selection Operator (LASSO) are employed to learn sparse feature representations under each semantic view; at the cross-semantic level, the contributions of different semantic views are adaptively characterized via KL divergence to produce a unified explanation. Extensive experiments demonstrate that HiSE outperforms existing methods in terms of fidelity, robustness, and cross-semantic explanation capability, while its lightweight framework incurs low computational overhead, enabling efficient application to large-scale, complex real-world heterogeneous graphs.","short_abstract":"Heterogeneous graph neural networks (HGNNs) have demonstrated remarkable performance in modeling complex relational data, however their interpretability in high-stakes applications remains a critical challenge. Existing explanation methods suffer from two major limitations: on the one hand, the generated explanations f...","url_abs":"https://arxiv.org/abs/2606.03495","url_pdf":"https://arxiv.org/pdf/2606.03495v1","authors":"[\"Zongrui Li\",\"Yuhang Zhao\",\"Ying Zhao\",\"Yuanzhao Guo\",\"Qiang Huang\",\"Yuan Tian\"]","published":"2026-06-02T11:12:01Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}