Deep Inductive Graph Representation Learning
Ryan A. Rossi, Rong Zhou, Nesreen K. Ahmed · IEEE Transactions on Knowledge and Data Engineering · 2018
This paper presents a general inductive graph representation learning framework called$\text{DeepGL}$for learning deep nodeandedge features that generalize across-networks. In particular,$\text{DeepGL}$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,$\text{DeepGL}$learnsrelational functions(each representing a feature) that naturally generalize across-networks and are therefore useful for graph-based transfer learning tasks. Moreover,$\text{DeepGL}$naturally supports attributed graphs, learns interpretable inductive graph representations, and is space-efficient (by learning sparse feature vectors). In addition,$\text{DeepGL}$is expressive, flexible with many interchangeable components, efficient with a time complexity of$\mathcal {O}(|E|)$, and scalable for large networks via an efficient parallel implementation. Compared with recent methods,$\text{DeepGL}$is (1)effectivefor across-network transfer learning tasksandlarge (attributed) graphs, (2)space-efficientrequiring up to 6x less memory, (3)fastwith up to 106x speedup in runtime performance, and (4)accuratewith an average improvement in AUC of 20 percent or more on many learning tasks and across a wide variety of networks.