On the Surprising Behaviour of node2vec
This addresses reliability issues in graph learning for researchers and practitioners, but it is incremental as it builds on existing node2vec methods.
The paper investigates the instability of node2vec graph embeddings with respect to parameter choices and proposes practical strategies to improve robustness.
Graph embedding techniques are a staple of modern graph learning research. When using embeddings for downstream tasks such as classification, information about their stability and robustness, i.e., their susceptibility to sources of noise, stochastic effects, or specific parameter choices, becomes increasingly important. As one of the most prominent graph embedding schemes, we focus on node2vec and analyse its embedding quality from multiple perspectives. Our findings indicate that embedding quality is unstable with respect to parameter choices, and we propose strategies to remedy this in practice.