This paper presents a general inductive graph representation learning framework called $\text{DeepGL}$DeepGL for learning deep node and edge features that generalize across-networks. In particular, $\text{DeepGL}$DeepGL begins by deriving a set of base features from the graph (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, $\text{DeepGL}$DeepGL learns relational functions (each representing a feature) that naturally generalize across-networks and are therefore useful for graph-based transfer learning tasks. Moreover, $\text{DeepGL}$DeepGL naturally supports attributed graphs, learns interpretable inductive graph representations, and is space-efficient (by learning sparse feature vectors). In addition, $\text{DeepGL}$DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of $\mathcal {O}(|E|)$O(|E|), and scalable for large networks via an efficient parallel implementation. Compared with recent methods, $\text{DeepGL}$DeepGL is (1) effective for across-network transfer learning tasks and large (attributed) graphs, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 106x speedup in runtime performance, and (4) accurate with an average improvement in AUC of 20 percent or more on many learning tasks and across a wide variety of networks.

中文翻译：

---

深度归纳图表示学习

本文提出了一个通用的归纳图表示学习框架，称为 $\text{DeepGL}$深度学习 用于学习深度节点 和泛化跨网络的边缘特征。特别是，$\text{DeepGL}$深度学习首先从图中导出一组基本特征（例如，graphlet 特征）并自动学习多层分层图表示，其中每个连续层利用前一层的输出来学习更高阶的特征。与之前的工作相反，$\text{DeepGL}$深度学习 学习 关系函数（每个代表一个特征）自然地跨网络泛化，因此对于基于图的迁移学习任务很有用。而且，$\text{DeepGL}$深度学习自然地支持属性图，学习可解释的归纳图表示，并且节省空间（通过学习稀疏特征向量）。此外，$\text{DeepGL}$深度学习 富有表现力，灵活，具有许多可互换的组件，效率高，时间复杂度为 $\mathcal {O}(|E|)$哦(|乙|)，并通过高效的并行实现为大型网络扩展。与最近的方法相比，$\text{DeepGL}$深度学习 是 (1) 有效的 用于跨网络迁移学习任务 和 大型（归因）图，（2） 节省空间 需要最多 6 倍的内存，(3) 快速地 运行时性能提升高达 106 倍，以及 (4) 准确的 在许多学习任务和各种网络中，AUC 平均提高了 20% 或更多。