arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.12007cs.LGcs.AI
收藏

张量视角拓扑图神经网络

Tensor-view Topological Graph Neural Network

New York University(纽约大学);Temple University(天普大学)

Tao Wen, Elynn Chen, Yuzhou Chen

AI总结:

针对现有图神经网络仅用局部邻域信息、存在多模态信息丢失与计算开销大的问题,提出结合张量学习的TTG-NN,通过解耦的TT与TG模块捕捉多尺度结构信息,推导了误差界,在多基准上优于20种现有方法。

摘要:

图分类是图结构数据的一项重要学习任务。图神经网络(GNNs)近年来在图学习领域受到越来越多的关注,且在诸多重要图问题上取得了显著提升。尽管现有GNNs达到了当前最优性能,但它们仅利用每个节点周围极有限邻域的局部信息,存在多模态信息丢失与计算量过大的开销问题。为解决这些问题,我们提出了一种新颖的张量视角拓扑图神经网络(TTG-NN),这是一类基于持续同调、图卷积与张量运算构建的简单却有效的拓扑深度学习模型。该新方法结合张量学习,能够同时捕捉局部与全局层面的张量视角拓扑(TT)结构信息以及张量视角图(TG)结构信息。在计算层面,为充分利用图的拓扑与结构特性,我们提出了两个灵活的TT与TG表示学习模块,二者将特征张量聚合与变换解耦,能够以更少的计算量学习并保留多模态结构。在理论层面,我们推导了所提出的张量变换层(TTL)的样本外与样本内均方近似误差的高概率界。真实数据实验表明,所提出的TTG-NN在各类图基准数据集上的表现优于20种当前最优方法。

英文摘要:

Graph classification is an important learning task for graph-structured data. Graph neural networks (GNNs) have recently gained growing attention in graph learning and have shown significant improvements in many important graph problems. Despite their state-of-the-art performances, existing GNNs only use local information from a very limited neighborhood around each node, suffering from loss of multi-modal information and overheads of excessive computation. To address these issues, we propose a novel Tensor-view Topological Graph Neural Network (TTG-NN), a class of simple yet effective topological deep learning built upon persistent homology, graph convolution, and tensor operations. This new method incorporates tensor learning to simultaneously capture Tensor-view Topological (TT), as well as Tensor-view Graph (TG) structural information on both local and global levels. Computationally, to fully exploit graph topology and structure, we propose two flexible TT and TG representation learning modules that disentangle feature tensor aggregation and transformation and learn to preserve multi-modal structure with less computation. Theoretically, we derive high probability bounds on both the out-of-sample and in-sample mean squared approximation errors for our proposed Tensor Transformation Layer (TTL). Real data experiments show that the proposed TTG-NN outperforms 20 state-of-the-art methods on various graph benchmarks.

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。

↑