LoNe Sampler: Graph node embeddings by coordinated local neighborhood sampling

TL;DR

LoNe Sampler introduces algorithms for discrete graph node embeddings via local neighborhood sampling, emphasizing theoretical rigor and efficient explicit vector map generation, improving scalability and interpretability.

Contribution

The paper presents a suite of algorithms for discrete node embeddings with rigorous theoretical analysis and a method to generate explicit vector maps without costly Gram matrix computations.

Findings

Algorithms are theoretically sound and scalable.

Explicit vector maps improve computational efficiency.

Experimental results confirm theoretical advantages.

Abstract

Local graph neighborhood sampling is a fundamental computational problem that is at the heart of algorithms for node representation learning. Several works have presented algorithms for learning discrete node embeddings where graph nodes are represented by discrete features such as attributes of neighborhood nodes. Discrete embeddings offer several advantages compared to continuous word2vec-like node embeddings: ease of computation, scalability, and interpretability. We present LoNe Sampler, a suite of algorithms for generating discrete node embeddings by Local Neighborhood Sampling, and address two shortcomings of previous work. First, our algorithms have rigorously understood theoretical properties. Second, we show how to generate approximate explicit vector maps that avoid the expensive computation of a Gram matrix for the training of a kernel model. Experiments on benchmark datasets confirm the theoretical findings and demonstrate the advantages of the proposed methods.