Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining graph model decisions, the interpretability of unsupervised node embeddings remains underexplored. To bridge this gap, we introduce DiSeNE (Disentangled and Self-Explainable Node Embedding), a framework that generates self-explainable embeddings in an unsupervised manner. Our method employs disentangled representation learning to produce dimension-wise interpretable embeddings, where each dimension is aligned with distinct topological structure of the graph. We formalize novel desiderata for disentangled and interpretable embeddings, which drive our new objective functions, optimizing simultaneously for both interpretability and disentanglement. Additionally, we propose several new metrics to evaluate representation quality and human interpretability. Extensive experiments across multiple benchmark datasets demonstrate the effectiveness of our approach.

翻译：节点表示（或称嵌入）是通过无监督结构相似性目标或监督任务学习得到的低维向量，用于捕捉节点特性。尽管近期研究集中于解释图模型决策，但无监督节点嵌入的可解释性仍未得到充分探索。为填补这一空白，我们提出了DiSeNE（解耦与自解释节点嵌入）框架，该框架能以无监督方式生成自解释嵌入。我们的方法采用解耦表示学习来生成维度可解释的嵌入，其中每个维度与图中不同的拓扑结构对齐。我们形式化地提出了解耦可解释嵌入的新需求准则，并据此构建了新的目标函数，同时优化可解释性与解耦性。此外，我们提出了若干新指标来评估表示质量与人类可解释性。在多个基准数据集上的大量实验证明了我们方法的有效性。