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 issues 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 subgraphs 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 redundancy 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 avoids repeated nodes by definition, but node sets can be irregular in size. To address this issue, we design a customized sparse data structure to efficiently store and index 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 structure 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.

翻译：基于子图的图表示学习（SGRL）因其在模型表达能力和泛化能力上的优势，近年来已成为图结构预测任务中的强大工具。多数现有SGRL模型面临计算效率问题，主要源于每个训练或测试查询都需要进行高成本的子图提取。近期提出的SUREL通过离线采样随机游走、在线拼接游走作为子图代理进行表示学习，显著加速了SGRL。得益于采样游走在不同查询间的可复用性，SUREL在可扩展性和预测精度方面取得了最先进的性能。然而，SUREL仍因采样游走中节点冗余而面临高计算开销。本文提出新型框架SUREL+，通过采用节点集合而非游走来表示子图，对SUREL进行升级。这种基于集合的表示从定义上避免了重复节点，但节点集合的规模可能不规则。为解决该问题，我们设计了定制化稀疏数据结构以高效存储和索引节点集合，并提供专用算子支持并行批量拼接。SUREL+采用模块化设计，支持多种集合采样器、结构特征和神经编码器，以弥补从游走降维至集合后的结构信息损失。通过链接预测、关系类型预测和高阶模式预测任务的广泛实验验证，SUREL+在保持相当甚至更优预测性能的同时，实现了3-11倍于SUREL的加速；与其他SGRL基线方法相比，SUREL+获得约20倍加速，并显著提升了预测精度。