提出无需任务依赖的节点表示解释方法，揭示影响表示的关键特征。
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
- 基于对比学习构建表示空间相似性函数，识别关键特征。
- 实验证明邻近与结构特征对节点表示影响显著。
- 适用于无监督与有监督场景，可解释性更强。
图表示学习在将图结构数据编码为潜在向量空间方面取得了显著成功，支持了多种下游任务。然而，这些节点表示仍不透明且难以解释。现有可解释性方法主要集中在有监督场景或解释单个表示维度，未能解决整体节点表示结构的解释问题。本文提出 TACENR（Task-Agnostic Contrastive Explanations for Node Representations），一种局部解释方法，能识别不仅包括属性特征，还包括邻近性和结构性特征中对表示贡献最大的部分。TACENR 基于对比学习，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关键作用。尽管本方法聚焦于任务无关解释，但也可应用于有监督场景。实验结果表明，邻近和结构特征在塑造节点表示中起重要作用，且其有监督变体在识别最具影响力特征方面表现媲美现有任务特定方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。