Interpreting Node Embedding Distances Through $n$-order Proximity Neighbourhoods
Abstract
In the field of node representation learning the task of interpreting latent dimensions has become a prominent, well-studied research topic. The contribution of this work focuses on appraising the interpretability of another rarely-exploited feature of node embeddings increasingly utilised in recommendation and consumption diversity studies: inter-node embedded distances. Introducing a new method to measure how understandable the distances between nodes are, our work assesses how well the proximity weights derived from a network before embedding relate to the node closeness measurements after embedding. Testing several classical node embedding models, our findings reach a conclusion familiar to practitioners albeit rarely cited in literature - the matrix factorisation model SVD is the most interpretable through 1, 2 and even higher-order proximities.
Cite
@article{arxiv.2401.08236,
title = {Interpreting Node Embedding Distances Through $n$-order Proximity Neighbourhoods},
author = {Dougal Shakespeare and Camille Roth},
journal= {arXiv preprint arXiv:2401.08236},
year = {2025}
}
Comments
Preprint of: Shakespeare et al., Interpreting Node Embedding Distances Through $n$-order Proximity Neighbourhoods, published in Complex Networks XV, edited by Federico Botta, Mariana Macedo, Hugo Barbosa, Ronaldo Menezes, 2024, Springer Cham reproduced with permission of Springer Cham. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-57515-0