面向持续图学习的拓扑感知图粗化框架
A Topology-aware Graph Coarsening Framework for Continual Graph Learning
AI总结：
针对流式图持续学习中拓扑保留低效及新旧任务相关性捕捉不足的问题，提出拓扑感知图粗化框架TA$\mathbb{CO}$，通过基于节点表示邻近度的图粗化算法构建缩减图以存储历史知识，实验证明其能有效近似原图学习过程。
摘要：
图上的持续学习解决的是在图数据以流式到达时训练图神经网络（GNN）的问题，此时模型在用新数据更新时往往会遗忘先前任务的知识。传统持续学习策略如Experience Replay可适配流式图，但这些方法常面临难以高效保留图拓扑结构以及无法捕捉新旧任务间相关性等挑战。为应对这些挑战，我们提出了TA$\mathbb{CO}$，一个拓扑感知的图粗化与持续学习框架，将先前任务的信息作为缩减图存储。在每个时间段，该缩减图通过与新图结合并对齐共享节点进行扩展，随后经历“缩小”过程进行缩减以维持稳定规模。我们设计了一种基于节点表示邻近度的图粗化算法，以高效缩减图并保留拓扑信息。我们通过实验证明，在缩减图上的学习过程可以近似在原图上的学习过程。我们的实验验证了所提框架在三个真实世界数据集上使用不同骨干GNN模型的有效性。
英文摘要：
Continual learning on graphs tackles the problem of training a graph neural network (GNN) where graph data arrive in a streaming fashion and the model tends to forget knowledge from previous tasks when updating with new data. Traditional continual learning strategies such as Experience Replay can be adapted to streaming graphs, however, these methods often face challenges such as inefficiency in preserving graph topology and incapability of capturing the correlation between old and new tasks. To address these challenges, we propose TA$\mathbb{CO}$, a (t)opology-(a)ware graph (co)arsening and (co)ntinual learning framework that stores information from previous tasks as a reduced graph. At each time period, this reduced graph expands by combining with a new graph and aligning shared nodes, and then it undergoes a "zoom out" process by reduction to maintain a stable size. We design a graph coarsening algorithm based on node representation proximities to efficiently reduce a graph and preserve topological information. We empirically demonstrate the learning process on the reduced graph can approximate that of the original graph. Our experiments validate the effectiveness of the proposed framework on three real-world datasets using different backbone GNN models.
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。
