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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Napoli, Rosario, Morabito, Gabriele, Celesti, Antonio, Villari, Massimo, Fazio, Maria
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914279561625600
author Napoli, Rosario
Morabito, Gabriele
Celesti, Antonio
Villari, Massimo
Fazio, Maria
author_facet Napoli, Rosario
Morabito, Gabriele
Celesti, Antonio
Villari, Massimo
Fazio, Maria
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12071
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread
Napoli, Rosario
Morabito, Gabriele
Celesti, Antonio
Villari, Massimo
Fazio, Maria
Machine Learning
Artificial Intelligence
68T30, 68T01, 68T05, 68W10
I.2.4; I.2.6; H.2.8; H.3.3
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.
title Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread
topic Machine Learning
Artificial Intelligence
68T30, 68T01, 68T05, 68W10
I.2.4; I.2.6; H.2.8; H.3.3
url https://arxiv.org/abs/2511.12071