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 2410.01367cs.LG
收藏

迈向具有可证明高阶表达能力的动态图神经网络

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power

Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学)

Zhe Wang, Tianjian Zhao, Zhen Zhang, Jiawei Chen, Sheng Zhou, Yan Feng, Chun Chen, Can Wang

AI总结:

本文提出 k-DWL 测试量化动态图神经网络表达能力,并设计 HopeDGN 通过聚合相邻节点对交互历史达到等价于 2-DWL 的能力,实验最高提升 3.12%。

摘要:

动态图神经网络(DyGNNs)因在演化图上学习表示而受到越来越多的研究关注。尽管它们有效,但现有 DyGNNs 有限的表达能力阻碍其捕捉动态图的重要演化模式。尽管一些工作尝试通过启发式特征增强表达能力,但仍缺乏具备可证明且可量化的高阶表达能力的 DyGNN 框架。为填补这一研究空白,我们首先提出 k 维动态 WL 测试(k-DWL),作为量化 DyGNNs 表达能力的参照算法。我们证明现有 DyGNNs 的表达能力以 1-DWL 测试为上界。为增强表达能力,我们提出具有高阶表达能力的动态图神经网络(HopeDGN),它通过聚合与相邻节点对的交互历史来更新中心节点对的表示。理论结果表明,HopeDGN 可达到与 2-DWL 测试等价的表达能力。随后,我们针对 HopeDGN 的局部变体给出基于 Transformer 的实现。实验结果显示,HopeDGN 实现了最高 3.12% 的性能提升,证明了 HopeDGN 的有效性。

英文摘要:

Dynamic Graph Neural Networks (DyGNNs) have garnered increasing research attention for learning representations on evolving graphs. Despite their effectiveness, the limited expressive power of existing DyGNNs hinders them from capturing important evolving patterns of dynamic graphs. Although some works attempt to enhance expressive capability with heuristic features, there remains a lack of DyGNN frameworks with provable and quantifiable high-order expressive power. To address this research gap, we firstly propose the k-dimensional Dynamic WL tests (k-DWL) as the referencing algorithms to quantify the expressive power of DyGNNs. We demonstrate that the expressive power of existing DyGNNs is upper bounded by the 1-DWL test. To enhance the expressive power, we propose Dynamic Graph Neural Network with High-order expressive power (HopeDGN), which updates the representation of central node pair by aggregating the interaction history with neighboring node pairs. Our theoretical results demonstrate that HopeDGN can achieve expressive power equivalent to the 2-DWL test. We then present a Transformer-based implementation for the local variant of HopeDGN. Experimental results show that HopeDGN achieved performance improvements of up to 3.12%, demonstrating the effectiveness of HopeDGN.

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。

↑