GraphFLEx: Structure Learning Framework for Large Expanding Graphs

TL;DR

GraphFLEx introduces a scalable, flexible framework for structure learning in large, evolving graphs, enabling efficient incremental updates and outperforming existing methods across diverse datasets.

Contribution

It presents a novel, unified approach that reduces computational costs by focusing on relevant node subsets, supporting multiple configurations for various graph learning scenarios.

Findings

Achieves state-of-the-art performance on 26 datasets.

Significantly improves scalability for large, dynamic graphs.

Supports 48 flexible configurations for diverse applications.

Abstract

Graph structure learning is a core problem in graph-based machine learning, essential for uncovering latent relationships and ensuring model interpretability. However, most existing approaches are ill-suited for large-scale and dynamically evolving graphs, as they often require complete re-learning of the structure upon the arrival of new nodes and incur substantial computational and memory costs. In this work, we propose GraphFLEx: a unified and scalable framework for Graph Structure Learning in Large and Expanding Graphs. GraphFLEx mitigates the scalability bottlenecks by restricting edge formation to structurally relevant subsets of nodes identified through a combination of clustering and coarsening techniques. This dramatically reduces the search space and enables efficient, incremental graph updates. The framework supports 48 flexible configurations by integrating diverse choices of learning paradigms, coarsening strategies, and clustering methods, making it adaptable to a wide range of graph settings and learning objectives. Extensive experiments across 26 diverse datasets and Graph Neural Network architectures demonstrate that GraphFLEx achieves state-of-the-art performance with significantly improved scalability.