oversquashing

This paper introduces addressable and cardinality-preserving global memory for message-passing neural networks via cross-attention slots, addressing the finite-capacity bottleneck of virtual nodes and improving performance on multiplicity-aware tasks.

本文介绍了 HMH，这是一种分层多尺度图神经网络框架，旨在解决异配图中的过平滑和过挤压问题。它利用基于 Haar 小波基的谱滤波器，实现了可扩展的学习，并在节点和图分类任务上取得了更好的性能。