Learning Role-based Graph Embeddings

Abstract

Random walks are at the heart of many existing network embedding methods. 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 vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and 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 16.55% while requiring on average 853x less space than existing methods on a variety of graphs.

StarAI workshop @ IJCAI 2018

References in corpus (1)

• Exponential Family Embeddings

Cited by in corpus (18)

• On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
• End to end learning and optimization on graphs
• Higher-order Graph Convolutional Networks
• A framework for second order eigenvector centralities and clustering coefficients
• HONE: Higher-Order Network Embeddings
• Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis
• Deep Graph Similarity Learning: A Survey
• Heterogeneous Network Motifs
• RiWalk: Fast Structural Node Embedding via Role Identification
• Dynamic Node Embeddings from Edge Streams
• Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings
• Latent Network Summarization: Bridging Network Embedding and Summarization
• Towards Improved Illicit Node Detection with Positive-Unlabelled Learning
• From Static to Dynamic Node Embeddings
• Temporal Network Sampling
• Bot-Match: Social Bot Detection with Recursive Nearest Neighbors Search
• Block-Approximated Exponential Random Graphs
• Network representation learning: A macro and micro view