论文标题
独自留下图表：解决过度的问题而不会重新打开
Leave Graphs Alone: Addressing Over-Squashing without Rewiring
论文作者
论文摘要
最近的作品研究了图形瓶颈在防止消息传播的图形神经网络中的远程信息传播中的作用，从而导致所谓的“过度点击”现象。作为一种补救措施，已经提出了图形的重新布线机制作为预处理步骤。 Graph Echo状态网络（GESNS）是图形的储层计算模型，其中节点嵌入是通过未经训练的消息通话函数递归计算的。在本文中，我们表明，GESN可以在六个杂种淋巴结分类任务上实现明显更好的准确性，而无需更改图形连接，从而提出了解决过度方面问题的不同途径。
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-squashing' phenomenon. As a remedy, graph rewiring mechanisms have been proposed as preprocessing steps. Graph Echo State Networks (GESNs) are a reservoir computing model for graphs, where node embeddings are recursively computed by an untrained message-passing function. In this paper, we show that GESNs can achieve a significantly better accuracy on six heterophilic node classification tasks without altering the graph connectivity, thus suggesting a different route for addressing the over-squashing problem.
