Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.

翻译：与仅追求推荐准确性相比，推荐模型的可解释性近年来受到更多关注。许多基于图的推荐方法借助注意力机制从信息路径中生成解释。然而，这些注意力权重原本是为模型准确性而非可解释性设计的。近期，已有研究者开始质疑基于注意力的可解释性，因为注意力权重在不同复现中不稳定，且未必符合人类直觉。受因果学习理论中反事实推理的启发，我们提出了一种面向路径推荐的新型可解释框架，其中通过学习路径的可解释权重来替代注意力权重。具体而言，我们从路径表示与路径拓扑结构两个角度分别设计了两种反事实推理算法。此外，不同于传统案例研究，我们还提出了一套包含定性与定量方法的可解释性评估方案。在三个真实数据集上的大量实验进一步验证了本方法的有效性与可靠性。