Deep Feature Learning for Graphs

Abstract

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.

References in corpus (2)

• Uncovering the overlapping community structure of complex networks in nature and society
• Carina: Interactive Million-Node Graph Visualization using Web Browser Technologies

Cited by in corpus (12)

• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• Learning Role-based Graph Embeddings
• Network Representation Learning: A Survey
• Inductive Representation Learning in Large Attributed Graphs
• A Framework for Generalizing Graph-based Representation Learning Methods
• Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis
• On Node Features for Graph Neural Networks
• LinkNBed: Multi-Graph Representation Learning with Entity Linkage
• Predicting Graph Categories from Structural Properties
• Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks
• RECS: Robust Graph Embedding Using Connection Subgraphs
• Noise-robust classification with hypergraph neural network