揭示MPNN嵌入距离背后的可解释子图机制
WILTing Trees: Interpreting the Distance Between MPNN Embeddings
- 基于最优传输构建可解释的图距离，利用WILT树分析子图影响
- 仅依赖少量功能重要子图就确定嵌入相对位置，效率高
- 适用于需要理解图神经网络决策依据的研究者
我们研究消息传递神经网络（MPNNs）在特定任务中学习的距离函数，旨在捕捉预测目标之间的功能性距离。这与以往将任意任务下的MPNN距离关联到忽略任务信息的图结构距离的方法形成对比。为弥补这一差距，我们将MPNN嵌入间的距离提炼为可解释的图距离。方法基于威斯费勒-莱曼标记树（WILT）上的最优传输，其边权重揭示了对嵌入距离有显著影响的子图。该方法推广了两种经典图核，并可在线性时间内计算。通过大量实验，我们证明MPNN通过聚焦于少量已知在领域内具有功能重要性的子图，来定义嵌入的相对位置。
原文摘要 · Abstract (English)
We investigate the distance function learned by message passing neural networks (MPNNs) in specific tasks, aiming to capture the functional distance between prediction targets that MPNNs implicitly learn. This contrasts with previous work, which links MPNN distances on arbitrary tasks to structural distances on graphs that ignore task-specific information. To address this gap, we distill the distance between MPNN embeddings into an interpretable graph distance. Our method uses optimal transport on the Weisfeiler Leman Labeling Tree (WILT), where the edge weights reveal subgraphs that strongly influence the distance between embeddings. This approach generalizes two well-known graph kernels and can be computed in linear time. Through extensive experiments, we demonstrate that MPNNs define the relative position of embeddings by focusing on a small set of subgraphs that are known to be functionally important in the domain.
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。