# Interpreting Node Embedding Distances Through n-order Proximity Neighbourhoods

arXiv: https://arxiv.org/abs/2401.08236 · HTML: https://mlsanity.com/paper/2401.08236/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2024.

## Built on by (most cited first, 2 of 2)

- [Disentangled and Self-Explainable Node Representation Learning](https://mlsanity.com/paper/2410.21043/) (2024)
- [Rethinking Node Representation Interpretation through Relation Coherence](https://mlsanity.com/paper/2411.00653/) (2024)

## Abstract (arXiv)

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.