Deep Inductive Graph Representation Learning

Ryan A. Rossi, Rong Zhou, Nesreen K. Ahmed

Abstract: This paper presents a general inductive graph representation learning framework called <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> for learning deep node <i>and</i> edge features that generalize across-networks. In particular, <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> 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, <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> learns <i>relational functions</i> (each representing a feature) that naturally generalize across-networks and are therefore useful for graph-based transfer learning tasks. Moreover, <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> naturally supports attributed graphs, learns interpretable inductive graph representations, and is space-efficient (by learning sparse feature vectors). In addition, <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> is expressive, flexible with many interchangeable components, efficient with a time complexity of <inline-formula><tex-math notation="LaTeX">$\mathcal {O}(|E|)$</tex-math></inline-formula> , and scalable for large networks via an efficient parallel implementation. Compared with recent methods, <inline-formula><tex-math notation="LaTeX">$\text{DeepGL}$</tex-math></inline-formula> is (1) <i>effective</i> for across-network transfer learning tasks <i>and</i> large (attributed) graphs, (2) <i>space-efficient</i> requiring up to 6x less memory, (3) <i>fast</i> with up to 106x speedup in runtime performance, and (4) <i>accurate</i> with an average improvement in AUC of 20 percent or more on many learning tasks and across a wide variety of networks.