Deep Feature Learning for Graphs
It addresses graph representation learning for large networks, offering improvements in efficiency and accuracy, but appears incremental as it builds on existing graph feature learning methods.
This paper tackles the problem of learning deep node and edge representations from large attributed graphs by introducing DeepGL, a general graph representation learning framework that automatically learns hierarchical features. The result shows DeepGL is effective for transfer learning, space-efficient with up to 6x less memory, fast with up to 182x speedup, and accurate with an average improvement of 20% or more on many tasks.
This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (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, DeepGL learns relational functions (each representing a feature) that generalize across-networks and therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable features, and is space-efficient (by learning sparse feature vectors). In addition, 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 the state-of-the-art method, DeepGL is (1) effective for across-network transfer learning tasks and attributed graph representation learning, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 182x speedup in runtime performance, and (4) accurate with an average improvement of 20% or more on many learning tasks.