用诊断分类器探测图神经网络是否包含图结构特征
Do graph neural network states contain graph properties?
- 设计无模型依赖的解释流程，用图论属性做特征探测
- 验证不同架构和数据集下GNN嵌入能反映图结构特性
- 适合研究GNN可解释性与模型信任度的学者参考
深度神经网络在众多任务中表现卓越，但其性能提升往往依赖于模型规模增大，导致内部表示更加复杂。可解释性技术（XAI）在机器学习模型解释方面取得显著进展，但图神经网络（GNNs）的非欧几里得特性使得现有XAI方法难以直接复用。尽管已有研究聚焦于GNN的实例级解释方法，但针对模型级方法的研究极少，且据我们所知，尚无工作尝试探查GNN嵌入中是否包含图结构属性。本文提出一种模型无关的GNN可解释性流水线，采用诊断分类器，将图论属性作为研究GNN表示学习中特征涌现的首选特征。该流程旨在跨多种架构和数据集探究并解释GNN的学得表示，深化对这些模型的理解与信任。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) achieve state-of-the-art performance on many tasks, but this often requires increasingly larger model sizes, which in turn leads to more complex internal representations. Explainability techniques (XAI) have made remarkable progress in the interpretability of ML models. However, the non-euclidean nature of Graph Neural Networks (GNNs) makes it difficult to reuse already existing XAI methods. While other works have focused on instance-based explanation methods for GNNs, very few have investigated model-based methods and, to our knowledge, none have tried to probe the embedding of the GNNs for structural graph properties. In this paper we present a model agnostic explainability pipeline for Graph Neural Networks (GNNs) employing diagnostic classifiers. We propose to consider graph-theoretic properties as the features of choice for studying the emergence of representations in GNNs. This pipeline aims to probe and interpret the learned representations in GNNs across various architectures and datasets, refining our understanding and trust in these models.
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。