Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread

TL;DR

This paper introduces a novel graph machine learning pipeline that incorporates a knowledge completion phase to uncover hidden relations, significantly improving the quality and interpretability of graph embeddings, demonstrated through a COVID-19 case study.

Contribution

It proposes a new GML pipeline with a knowledge completion step focusing on transitive relations, reshaping graph topology and enhancing embedding quality.

Findings

Significant changes in embedding space geometry after knowledge completion.

Transformative impact on graph representation quality.

Effective modeling of hidden connections improves downstream tasks.

Abstract

The rise of graph-structured data has driven major advances in Graph Machine Learning (GML), where graph embeddings (GEs) map features from Knowledge Graphs (KGs) into vector spaces, enabling tasks like node classification and link prediction. However, since GEs are derived from explicit topology and features, they may miss crucial implicit knowledge hidden in seemingly sparse datasets, affecting graph structure and their representation. We propose a GML pipeline that integrates a Knowledge Completion (KC) phase to uncover latent dataset semantics before embedding generation. Focusing on transitive relations, we model hidden connections with decay-based inference functions, reshaping graph topology, with consequences on embedding dynamics and aggregation processes in GraphSAGE and Node2Vec. Experiments show that our GML pipeline significantly alters the embedding space geometry, demonstrating that its introduction is not just a simple enrichment but a transformative step that redefines graph representation quality.