SPARC: Spectral Architectures Tackling the Cold-Start Problem in Graph Learning

Détail du document

Identifiant

oai:arXiv.org:2411.01532

Sujet

Computer Science - Machine Learnin... Statistics - Machine Learning

Auteur

Jacobs, Yahel Dayan, Reut Shaham, Uri

Catégorie

Computer Science

Année

2024

Date de référencement

26/02/2025

Mots clés

methods learning

Métrique

Résumé

Graphs play a central role in modeling complex relationships in data, yet most graph learning methods falter when faced with cold-start nodes--new nodes lacking initial connections--due to their reliance on adjacency information.

To tackle this, we propose SPARC, a groundbreaking framework that introduces a novel approach to graph learning by utilizing generalizable spectral embeddings.

With a simple yet powerful enhancement, SPARC empowers state-of-the-art methods to make predictions on cold-start nodes effectively.

By eliminating the need for adjacency information during inference and effectively capturing the graph's structure, we make these methods suitable for real-world scenarios where new nodes frequently appear.

Experimental results demonstrate that our framework outperforms existing models on cold-start nodes across tasks such as node classification, node clustering, and link prediction.

SPARC provides a solution to the cold-start problem, advancing the field of graph learning.

Jacobs, Yahel,Dayan, Reut,Shaham, Uri, 2024, SPARC: Spectral Architectures Tackling the Cold-Start Problem in Graph Learning

Document

Ouvrir

Source