解决GNN注意力机制在扰动下不稳定的可解释性问题
Faithful Interpretation for Graph Neural Networks
- 提出忠实图注意力解释框架FGAI，增强解释稳定性
- 在添加边或节点等扰动下仍保持注意力分布可靠
- 适合需要可信解释的GNN应用，如医疗、金融风控
当前，注意力机制在图神经网络（GNNs）中备受关注，如图注意力网络（GATs）和图变压器（GTs）。这不仅因为其显著提升性能，更因其能提供模型行为的清晰解释，而这些行为常被视为黑箱。然而，基于注意力的GNN在训练和测试阶段面对各种扰动（如新增边或节点）时，其可解释性表现出不稳定性。本文提出一种解决方案，引入新概念——忠实图注意力解释（FGAI）。FGAI具备四个关键性质：对解释和最终输出分布的稳定性和敏感性。基于此，我们提出一种高效方法获取FGAI，可视为对标准注意力型GNN的即插即用改进。为验证该方案，我们设计了两个新型图解释评估指标。实验结果表明，FGAI在多种扰动和随机性条件下均展现出更强的稳定性，并保持注意力的可解释性，使其成为更忠实可靠的解释工具。
原文摘要 · Abstract (English)
Currently, attention mechanisms have garnered increasing attention in Graph Neural Networks (GNNs), such as Graph Attention Networks (GATs) and Graph Transformers (GTs). It is not only due to the commendable boost in performance they offer but also its capacity to provide a more lucid rationale for model behaviors, which are often viewed as inscrutable. However, Attention-based GNNs have demonstrated instability in interpretability when subjected to various sources of perturbations during both training and testing phases, including factors like additional edges or nodes. In this paper, we propose a solution to this problem by introducing a novel notion called Faithful Graph Attention-based Interpretation (FGAI). In particular, FGAI has four crucial properties regarding stability and sensitivity to interpretation and final output distribution. Built upon this notion, we propose an efficient methodology for obtaining FGAI, which can be viewed as an ad hoc modification to the canonical Attention-based GNNs. To validate our proposed solution, we introduce two novel metrics tailored for graph interpretation assessment. Experimental results demonstrate that FGAI exhibits superior stability and preserves the interpretability of attention under various forms of perturbations and randomness, which makes FGAI a more faithful and reliable explanation tool.
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。