Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
基于Mamba的图卷积网络:通过选择性状态空间解决过平滑问题
机构 * Jilin University(吉林大学) ; The Hong Kong Polytechnic University(香港理工大学)
AI总结 本文提出MbaGCN,通过引入Mamba范式,解决图神经网络中的过平滑问题,通过三种核心组件提升深度GNN模型的灵活性和可扩展性。
Comments Accepted by The Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2025)