GraphFLEx: Structure Learning Framework for Large Expanding Graphs

2025-05-18

AI Summary

To address the prohibitive computational and memory overhead of full-graph retraining in large-scale dynamic graph structure learning, this paper proposes the first incremental and scalable graph structure learning framework. The method innovatively integrates graph clustering with multi-granularity graph coarsening to jointly identify structurally relevant node subsets, drastically reducing the search space. It supports incremental optimization and is compatible with diverse GNN architectures, enabling efficient real-time topology updates. The framework is highly generalizable, offering 48 configurable strategies for task-specific adaptation. Evaluated on 26 benchmark datasets, it achieves state-of-the-art performance, reduces peak training memory consumption by up to 73%, and accelerates inference by up to 5.2×, effectively overcoming scalability bottlenecks in dynamic graph structure learning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Learning graph structures in large, dynamically evolving graphs
• Reducing computational costs for incremental graph updates
• Improving scalability while maintaining model interpretability

Innovation

• Combines clustering and coarsening for scalable learning
• Enables efficient incremental graph updates
• Supports 48 flexible configurations for adaptability