Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Abstract

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph -- a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to $90\%$. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.

References in corpus (6)

• Fast unfolding of communities in large networks
• LINE: Large-scale Information Network Embedding
• Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities
• HARP: Hierarchical Representation Learning for Networks
• Empirical Comparison of Algorithms for Network Community Detection
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

Cited by in corpus (1)

• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels