Learning Edge Representations via Low-Rank Asymmetric Projections

Abstract

We propose a new method for embedding graphs while preserving directed edge information. Learning such continuous-space vector representations (or embeddings) of nodes in a graph is an important first step for using network information (from social networks, user-item graphs, knowledge bases, etc.) in many machine learning tasks. Unlike previous work, we (1) explicitly model an edge as a function of node embeddings, and we (2) propose a novel objective, the "graph likelihood", which contrasts information from sampled random walks with non-existent edges. Individually, both of these contributions improve the learned representations, especially when there are memory constraints on the total size of the embeddings. When combined, our contributions enable us to significantly improve the state-of-the-art by learning more concise representations that better preserve the graph structure. We evaluate our method on a variety of link-prediction task including social networks, collaboration networks, and protein interactions, showing that our proposed method learn representations with error reductions of up to 76% and 55%, on directed and undirected graphs. In addition, we show that the representations learned by our method are quite space efficient, producing embeddings which have higher structure-preserving accuracy but are 10 times smaller.

References in corpus (1)

• DeepWalk: Online Learning of Social Representations

Cited by in corpus (5)

• VERSE: Versatile Graph Embeddings from Similarity Measures
• Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
• Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• Unsupervised Differentiable Multi-aspect Network Embedding