LoNe Sampler: Graph node embeddings by coordinated local neighborhood sampling
This work provides a more efficient and theoretically grounded method for graph node embeddings, which is incremental but beneficial for researchers and practitioners in graph machine learning.
The paper tackles the problem of generating discrete node embeddings for graph representation learning by introducing LoNe Sampler, a suite of algorithms that address theoretical gaps and computational inefficiencies in prior work, achieving improved scalability and interpretability as validated on benchmark datasets.
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.