Unsupervised Framework for Evaluating and Explaining Structural Node Embeddings of Graphs

TL;DR

This paper introduces an unsupervised framework for evaluating and explaining structural node embeddings in graphs, aiding data scientists in selecting and understanding the most promising embeddings without supervision.

Contribution

It presents the first unsupervised framework for ranking and explaining structural graph embeddings, providing quality scores and interpretability insights.

Findings

Framework assigns an aggregate quality score to structural embeddings.

Provides insights into learned node features and their representation.

Enhances explainability of complex embedding algorithms.

Abstract

An embedding is a mapping from a set of nodes of a network into a real vector space. Embeddings can have various aims like capturing the underlying graph topology and structure, node-to-node relationship, or other relevant information about the graph, its subgraphs or nodes themselves. A practical challenge with using embeddings is that there are many available variants to choose from. Selecting a small set of most promising embeddings from the long list of possible options for a given task is challenging and often requires domain expertise. Embeddings can be categorized into two main types: classical embeddings and structural embeddings. Classical embeddings focus on learning both local and global proximity of nodes, while structural embeddings learn information specifically about the local structure of nodes' neighbourhood. For classical node embeddings there exists a framework which helps data scientists to identify (in an unsupervised way) a few embeddings that are worth further investigation. Unfortunately, no such framework exists for structural embeddings. In this paper we propose a framework for unsupervised ranking of structural graph embeddings. The proposed framework, apart from assigning an aggregate quality score for a structural embedding, additionally gives a data scientist insights into properties of this embedding. It produces information which predefined node features the embedding learns, how well it learns them, and which dimensions in the embedded space represent the predefined node features. Using this information the user gets a level of explainability to an otherwise complex black-box embedding algorithm.