TACENR：任务无关的节点表示对比解释
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
AI总结：
本文提出TACENR，一种任务无关的节点表示对比解释方法，通过对比学习识别节点表示空间中对节点表示贡献最大的属性、接近性和结构性特征。
摘要：
图表示学习在将图结构数据编码到潜在向量空间中取得了显著成功，使各种下游任务成为可能。然而，这些节点表示仍然不透明且难以解释。现有的可解释性方法主要集中在监督设置或解释单个表示维度，留下了解释节点表示整体结构的空白。在本文中，我们提出了TACENR（任务无关的节点表示对比解释），一种局部解释方法，不仅识别属性特征，还识别在表示空间中贡献最大的接近性和结构性特征。TACENR基于对比学习，通过学习表示空间中的相似性函数，揭示哪些特征在节点表示中起重要作用。虽然我们的重点是任务无关的解释，但TACENR也可以应用于监督场景。实验结果表明，接近性和结构性特征在塑造节点表示中起重要作用，且我们的监督变体在识别最具影响力的特征方面与现有任务特定方法表现相当。
英文摘要：
Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these node representations remain opaque and difficult to interpret. Existing explainability methods primarily focus on supervised settings or on explaining individual representation dimensions, leaving a critical gap in explaining the overall structure of node representations. In this paper, we propose TACENR (Task-Agnostic Contrastive Explanations for Node Representations), a local explanation method that identifies not only attribute features but also proximity and structural ones that contribute the most in the representation space. TACENR builds on contrastive learning, through which we learn a similarity function in the representation space, revealing which are the features that play an important role in the representation of a node. While our focus is on task-agnostic explanations, TACENR can be applied to supervised scenarios as well. Experimental results demonstrate that proximity and structural features play a significant role in shaping node representations and that our supervised variant performs comparably to existing task-specific approaches in identifying the most impactful features.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
