A Differential Geometric View and Explainability of GNN on Evolving Graphs
A Differential Geometric View and Explainability of GNN on Evolving Graphs
复制标题
DOI：
10.48550/arxiv.2403.06425
复制
发表时间：
2024-03
期刊：
影响因子：
--
通讯作者：
Yazheng Liu;Xi Zhang;Sihong Xie
中科院分区：
文献类型：
--
作者：
Yazheng Liu;Xi Zhang;Sihong Xie
图在社交网络和生物化学中无处不在，其中图神经网络（GNN）是最先进的预测模型。图形可以不断演化，因此必须正式建模并理解经过训练的GNN如何响应图形演化。我们提出了一个光滑的参数化GNN预测分布使用公理属性，其中分布是在一个高维嵌入空间内的低维流形。我们利用微分几何的观点来模拟流形上的光滑曲线的分布演化。我们reparameterized家庭的流形上的曲线，并设计一个凸优化问题，找到一个独特的曲线，简洁地近似人类的解释分布的演变。在节点分类、链接预测和进化图分类任务上的大量实验表明，该方法比现有方法具有更好的稀疏性、忠实性和直观性。
Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction. Graphs can be evolving and it is vital to formally model and understand how a trained GNN responds to graph evolution. We propose a smooth parameterization of the GNN predicted distributions using axiomatic attribution, where the distributions are on a low-dimensional manifold within a high-dimensional embedding space. We exploit the differential geometric viewpoint to model distributional evolution as smooth curves on the manifold. We reparameterize families of curves on the manifold and design a convex optimization problem to find a unique curve that concisely approximates the distributional evolution for human interpretation. Extensive experiments on node classification, link prediction, and graph classification tasks with evolving graphs demonstrate the better sparsity, faithfulness, and intuitiveness of the proposed method over the state-of-the-art methods.