SUREL+：从游走到集合，实现可扩展的基于子图的图表示学习
SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
AI总结：
SUREL+通过将子图表示为节点集而非游走，消除了节点重复，设计了定制稀疏数据结构和并行连接算子，在保持或提升预测精度的同时，实现了对SUREL的3-11倍加速和对其他基线的约20倍加速。
摘要：
基于子图的图表示学习（SGRL）近年来因其在模型表达能力和泛化能力方面的优势，已成为图上的许多预测任务中的强大工具。大多数先前的SGRL模型面临与每个训练或测试查询的子图提取高成本相关的计算挑战。最近，提出了SUREL来加速SGRL，它离线采样随机游走，并在线连接这些游走作为子图的代理进行表示学习。得益于采样游走在不同查询之间的可重用性，SUREL在可扩展性和预测准确性方面达到了最先进的性能。然而，SUREL仍然因采样游走中的节点重复而遭受高计算开销。在这项工作中，我们提出了一个新颖的框架SUREL+，通过使用节点集而不是游走来表示子图，从而升级了SUREL。这种基于集合的表示通过定义消除了重复节点，但集合的大小也可能不规则。为了解决这个问题，我们设计了一种定制的稀疏数据结构来高效存储和访问节点集，并提供了一种专门的运算符来并行批量连接它们。SUREL+是模块化的，支持多种类型的集合采样器、结构特征和神经编码器，以补充从游走到集合的缩减后丢失的结构信息。我们进行了大量实验，在链接、关系类型和高阶模式的预测任务中验证了SUREL+。SUREL+实现了SUREL的3-11倍加速，同时保持相当或更好的预测性能；与其他SGRL基线相比，SUREL+实现了约20倍的加速，并显著提高了预测准确性。
英文摘要：
Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful tool in many prediction tasks on graphs due to its advantages in model expressiveness and generalization ability. Most previous SGRL models face computational challenges associated with the high cost of subgraph extraction for each training or test query. Recently, SUREL was proposed to accelerate SGRL, which samples random walks offline and joins these walks online as a proxy of subgraph for representation learning. Thanks to the reusability of sampled walks across different queries, SUREL achieves state-of-the-art performance in terms of scalability and prediction accuracy. However, SUREL still suffers from high computational overhead caused by node duplication in sampled walks. In this work, we propose a novel framework SUREL+ that upgrades SUREL by using node sets instead of walks to represent subgraphs. This set-based representation eliminates repeated nodes by definition but can also be irregular in size. To address this issue, we design a customized sparse data structure to efficiently store and access node sets and provide a specialized operator to join them in parallel batches. SUREL+ is modularized to support multiple types of set samplers, structural features, and neural encoders to complement the structural information loss after the reduction from walks to sets. Extensive experiments have been performed to validate SUREL+ in the prediction tasks of links, relation types, and higher-order patterns. SUREL+ achieves 3-11$\times$ speedups of SUREL while maintaining comparable or even better prediction performance; compared to other SGRL baselines, SUREL+ achieves $\sim$20$\times$ speedups and significantly improves the prediction accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
