论文标题
Space4Hgnn：一个新颖，模块化和可重现的平台，用于评估异质图神经网络
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
论文作者
论文摘要
异质图神经网络（HGNN）已成功地用于各种任务中，但是由于不同的架构和应用的场景，我们无法准确地知道HGNN不同设计维度的重要性。此外，在HGNN的研究界，实施和评估各种任务仍然需要大量的人为努力。为了减轻这些问题，我们首先提出了一个统一的框架，涵盖大多数HGNN，包括三个组件：异质线性变换，异质图转换和异质消息传递层。然后，我们通过基于统一框架来定义HGNN的设计空间来构建平台Space4Hgnn，该框架提供了模块化的组件，可再现的实现和HGNN的标准化评估。最后，我们进行实验以分析不同设计的效果。有了发现的见解，我们将凝结的设计空间提炼出来并验证其有效性。
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform Space4HGNN by defining a design space for HGNNs based on the unified framework, which offers modularized components, reproducible implementations, and standardized evaluation for HGNNs. Finally, we conduct experiments to analyze the effect of different designs. With the insights found, we distill a condensed design space and verify its effectiveness.
