COMBA：用于具有上下文门控状态空间模型的大型图学习的跨批次聚合
COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models
AI总结：
COMBA通过图上下文门控和跨批次聚合技术，提升大规模图学习的效率和性能。
摘要：
状态空间模型（SSMs）最近在建模长程依赖性序列数据中崭露头角，其计算成本远低于现代替代方案，如Transformer。将SSMs扩展到图结构数据，特别是大规模图数据，是一个重大挑战，因为SSMs是序列模型，而图的体积庞大，将图转换为序列以进行有效学习非常昂贵。在本文中，我们提出COMBA以利用状态空间模型进行大规模图学习，其两个关键创新是图上下文门控和跨批次聚合。图上下文指的是每个节点的不同邻域步数，图上下文门控使COMBA能够利用此类上下文来学习最佳的邻居聚合控制。对于每个图上下文，COMBA以批次方式采样节点，并训练图神经网络（GNN），信息在跨批次中聚合，使COMBA能够扩展到大规模图。我们的理论研究指出，跨批次聚合保证了比不进行聚合的GNN训练更低的误差。在基准网络上的实验显示，与基线方法相比，有显著的性能提升。代码和基准数据集将向公众发布。
英文摘要：
State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs are sequence models and the shear graph volumes make it very expensive to convert graphs as sequences for effective learning. In this paper, we propose COMBA to tackle large graph learning using state space models, with two key innovations: graph context gating and cross batch aggregation. Graph context refers to different hops of neighborhood for each node, and graph context gating allows COMBA to use such context to learn best control of neighbor aggregation. For each graph context, COMBA samples nodes as batches, and train a graph neural network (GNN), with information being aggregated cross batches, allowing COMBA to scale to large graphs. Our theoretical study asserts that cross-batch aggregation guarantees lower error than training GNN without aggregation. Experiments on benchmark networks demonstrate significant performance gains compared to baseline approaches. Code and benchmark datasets will be released for public access.
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。
