DINE: Dimensional Interpretability of Node Embeddings

TL;DR

This paper introduces DINE, a method to enhance the interpretability of node embeddings by making their dimensions more understandable, while maintaining their effectiveness in graph tasks like link prediction.

Contribution

The paper develops new metrics for global interpretability of node embeddings and proposes DINE, a novel approach to retrofit existing embeddings for better interpretability without losing performance.

Findings

DINE significantly improves interpretability of node embeddings.

Enhanced embeddings retain high accuracy in link prediction.

Metrics effectively measure global interpretability.

Abstract

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches to map nodes into a latent vector space, allowing their use for various graph tasks. Despite their success, only few studies have focused on explaining node embeddings locally. Moreover, global explanations of node embeddings remain unexplored, limiting interpretability and debugging potentials. We address this gap by developing human-understandable explanations for dimensions in node embeddings. Towards that, we first develop new metrics that measure the global interpretability of embedding vectors based on the marginal contribution of the embedding dimensions to predicting graph structure. We say that an embedding dimension is more interpretable if it can faithfully map to an understandable sub-structure in the input graph - like community structure. Having observed that standard node embeddings have low interpretability, we then introduce DINE (Dimension-based Interpretable Node Embedding), a novel approach that can retrofit existing node embeddings by making them more interpretable without sacrificing their task performance. We conduct extensive experiments on synthetic and real-world graphs and show that we can simultaneously learn highly interpretable node embeddings with effective performance in link prediction.