首个可解释超图神经网络的工具，支持局部与全局解释。
Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts
- 通过采样子超图实现输入归因，兼顾准确与简洁
- 在8个数据集上平均提升25个百分点的解释保真度
- 适合关注模型可解释性的研究人员和开发者
超图神经网络是一类利用消息传递范式在超图上学习的强大模型，超图是描述高阶交互关系数据的图结构泛化形式。然而，这类模型缺乏天然可解释性，其可解释性研究极为有限。我们提出SHypX，首个面向超图神经网络的模型无关后处理解释器，可提供局部与全局解释。在实例层面，通过离散采样优化的解释子超图实现输入归因，保证忠实性与简洁性；在模型层面，采用无监督概念提取生成全局解释子超图。在四个真实世界和四个新型合成超图数据集上的大量实验表明，该方法能生成高质量解释，并可在忠实性与简洁性之间按用户需求权衡，平均比基线提升25个百分点的保真度。
原文摘要 · Abstract (English)
Hypergraph neural networks are a class of powerful models that leverage the message passing paradigm to learn over hypergraphs, a generalization of graphs well-suited to describing relational data with higher-order interactions. However, such models are not naturally interpretable, and their explainability has received very limited attention. We introduce SHypX, the first model-agnostic post-hoc explainer for hypergraph neural networks that provides both local and global explanations. At the instance-level, it performs input attribution by discretely sampling explanation subhypergraphs optimized to be faithful and concise. At the model-level, it produces global explanation subhypergraphs using unsupervised concept extraction. Extensive experiments across four real-world and four novel, synthetic hypergraph datasets demonstrate that our method finds high-quality explanations which can target a user-specified balance between faithfulness and concision, improving over baselines by 25 percent points in fidelity on average.
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。