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 2211.16494cs.LGcs.AIcs.NEstat.ML
收藏

论图神经网络对顶点间交互进行建模的能力

On the Ability of Graph Neural Networks to Model Interactions Between Vertices

Tel Aviv University(特拉维夫大学)

Noam Razin, Tom Verbin, Nadav Cohen

AI总结:

本文通过分离秩形式化GNNs对顶点交互的建模能力,发现其由划分的游走索引决定,并提出边稀疏化算法WIS以在移除边时保留该能力且提升预测精度。

摘要:

图神经网络(GNNs)被广泛用于对表示为图顶点的实体间的复杂交互进行建模。尽管近期在理论上对GNNs的表达能力进行了分析,但仍缺乏对其交互建模能力的正式刻画。本文旨在填补这一空白。通过一种称为分离秩(separation rank)的既有度量来形式化交互强度,我们量化了特定GNNs对给定顶点子集及其补集(即输入顶点给定划分的两侧)之间的交互进行建模的能力。我们的结果表明,建模交互的能力主要由该划分的游走索引(walk index)决定,这是一种由从划分边界出发的游走数量定义的图论特征。使用常见GNN架构的实验证实了这一发现。作为我们理论的实际应用,我们设计了一种名为Walk Index Sparsification(WIS)的边稀疏化算法,该算法在移除输入边时能保留GNN对交互进行建模的能力。WIS简单且计算高效,在我们的实验中,就诱导预测准确性而言,它明显优于其他替代方法。更广泛地说,它展示了通过理论分析GNNs所能建模的交互来改进GNNs的潜力。

英文摘要:

Graph neural networks (GNNs) are widely used for modeling complex interactions between entities represented as vertices of a graph. Despite recent efforts to theoretically analyze the expressive power of GNNs, a formal characterization of their ability to model interactions is lacking. The current paper aims to address this gap. Formalizing strength of interactions through an established measure known as separation rank, we quantify the ability of certain GNNs to model interaction between a given subset of vertices and its complement, i.e. between the sides of a given partition of input vertices. Our results reveal that the ability to model interaction is primarily determined by the partition's walk index -- a graph-theoretical characteristic defined by the number of walks originating from the boundary of the partition. Experiments with common GNN architectures corroborate this finding. As a practical application of our theory, we design an edge sparsification algorithm named Walk Index Sparsification (WIS), which preserves the ability of a GNN to model interactions when input edges are removed. WIS is simple, computationally efficient, and in our experiments has markedly outperformed alternative methods in terms of induced prediction accuracy. More broadly, it showcases the potential of improving GNNs by theoretically analyzing the interactions they can model.

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。

↑