PANDA:超越重连的扩展宽度感知消息传递
PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
AI总结:
本文提出PANDA,一种扩展宽度感知的消息传递范式,通过选择性扩展高中心性节点的宽度来缓解图神经网络的过度压缩问题,实验证明其优于现有重连方法。
摘要:
图神经网络(GNN)领域的最新研究识别出一个关键问题,即“过度压缩”,它源于图结构中的瓶颈现象,阻碍了长距离信息的传播。先前的工作提出了多种图重连概念,旨在优化图的空间或谱属性以促进信号传播。然而,此类方法不可避免地会恶化原始图拓扑,可能导致信息流失真。为解决这一问题,我们引入了一种扩展宽度感知(PANDA)消息传递,这是一种新的消息传递范式,其中具有高中心性(可能是过度压缩的潜在来源)的节点被选择性地扩展宽度,以封装来自远处节点不断增长的信号流入。实验结果表明,我们的方法优于现有的重连方法,表明选择性地扩展节点的隐藏状态可以作为解决过度压缩问题的图重连的有力替代方案。
英文摘要:
Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an expanded width-aware (PANDA) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.
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。