A Framework for Generalizing Graph-based Representation Learning Methods

Abstract

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, we introduce the notion of attributed random walks which serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.1% while requiring on average 853 times less space than existing methods on a variety of graphs from several domains.

References in corpus (9)

• Inductive Representation Learning on Large Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Biological network comparison using graphlet degree distribution
• Link Prediction Based on Local Random Walk
• Graph Metrics for Temporal Networks
• Role Discovery in Networks
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• Deep Feature Learning for Graphs
• Estimation of Graphlet Statistics

Cited by in corpus (6)

• On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
• MILE: A Multi-Level Framework for Scalable Graph Embedding
• Inductive Representation Learning in Large Attributed Graphs
• HONE: Higher-Order Network Embeddings
• Dynamic Node Embeddings from Edge Streams
• Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Games