arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.09943cs.LGcs.SI
收藏

无限时域图滤波器:利用幂级数增强稀疏信息聚合

Infinite-Horizon Graph Filters: Leveraging Power Series to Enhance Sparse Information Aggregation

Key Laboratory of High Confidence Software Technologies (Peking University)(北京大学高可信软件技术重点实验室);University of Toronto(多伦多大学);Ministry of Education(教育部);School of Computer Science, Peking University(北京大学计算机学院);Big Data Technology Research Center, Nanhu Laboratory(南湖实验室大数据技术研究中心)

Ruizhe Zhang, Xinke Jiang, Yuchen Fang, Jiayuan Luo, Yongxin Xu, Yichen Zhu, Xu Chu, Junfeng Zhao, Yasha Wang

AI总结:

针对GNN感受野受限问题,提出基于幂级数的无限感受野图滤波器GPFN,理论证明通用性,实验验证其优于现有方法。

摘要:

图神经网络(GNNs)在各种图学习任务中表现出显著的有效性,尤其是近年来基于消息传递的方法。然而,它们的性能常常受到有限感受野的限制,这一挑战在稀疏图存在时变得更加严峻。鉴于幂级数具有无限展开能力,我们提出了一种新颖的图幂滤波器神经网络(GPFN),通过采用幂级数图滤波器来增强感受野,从而提升节点分类性能。具体而言,我们的GPFN设计了一种基于收敛幂级数构建具有无限感受野的图滤波器的新方法,该方法可在谱域和空间域进行分析。此外,我们从理论上证明GPFN是一个通用框架,能够整合任何幂级数并捕获长距离依赖关系。最后,在三个数据集上的实验结果表明,我们的GPFN优于最先进的基线方法。

英文摘要:

Graph Neural Networks (GNNs) have shown considerable effectiveness in a variety of graph learning tasks, particularly those based on the message-passing approach in recent years. However, their performance is often constrained by a limited receptive field, a challenge that becomes more acute in the presence of sparse graphs. In light of the power series, which possesses infinite expansion capabilities, we propose a novel Graph Power Filter Neural Network (GPFN) that enhances node classification by employing a power series graph filter to augment the receptive field. Concretely, our GPFN designs a new way to build a graph filter with an infinite receptive field based on the convergence power series, which can be analyzed in the spectral and spatial domains. Besides, we theoretically prove that our GPFN is a general framework that can integrate any power series and capture long-range dependencies. Finally, experimental results on three datasets demonstrate the superiority of our GPFN over state-of-the-art baselines.

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。

↑