提出概念图卷积，让GNN推理过程更透明
Concept Graph Convolutions: Message Passing in the Concept Space
- 在原始节点与概念表示间进行消息传递
- 保持任务性能的同时提升概念演化可视性
- 适合关注模型可解释性的研究者
图神经网络的可信度受限于其黑箱推理过程。已有方法通过消息传递后的隐式表示提取概念解释，但无法解释消息传递本身。为此，我们提出概念图卷积（Concept Graph Convolution），首个面向节点级概念设计的图卷积层，实现对原始表示与概念表示的联合消息传递，使用结构化和注意力加权的边。还提出了仅在概念空间操作的纯版本。实验表明，该方法在保持竞争性任务准确率的同时，显著提升了对概念随卷积步骤演化的洞察力。
原文摘要 · Abstract (English)
The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanations extracted from the latent representations obtained after message passing. However, these explanations fall short of explaining the message passing process itself. To this aim, we propose the Concept Graph Convolution, the first graph convolution designed to operate on node-level concepts for improved interpretability. The proposed convolutional layer performs message passing on a combination of raw and concept representations using structural and attention-based edge weights. We also propose a pure variant of the convolution, only operating in the concept space. Our results show that the Concept Graph Convolution allows to obtain competitive task accuracy, while enabling an increased insight into the evolution of concepts across convolutional steps.
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。