提出可扩展的动态图结构学习框架，支持高效增量更新。
GraphFLEx: Structure Learning Framework for Large Expanding Graphs
- 通过聚类与粗化缩小边搜索空间，实现增量更新
- 在26个数据集上达到顶尖性能，显著提升可扩展性
- 48种配置灵活适配不同图场景和学习目标
图结构学习是基于图的机器学习中的核心问题，对揭示潜在关系和保障模型可解释性至关重要。然而，现有方法大多不适用于大规模动态演化图，因新节点到来时通常需重新完整学习结构，导致计算和内存开销巨大。本文提出GraphFLEx：一种面向大规模动态图的统一且可扩展的图结构学习框架。该框架通过结合聚类与粗化技术，仅在结构相关的节点子集中限制边的生成，大幅缩减搜索空间，实现高效、增量式的图结构更新。框架支持48种灵活配置，融合多种学习范式、粗化策略和聚类方法，可适应广泛的图设置与学习目标。在26个多样化数据集及多种图神经网络架构上的大量实验表明，GraphFLEx在保持显著可扩展性的同时，实现了领先性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。