Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space

2025-01-26 · Xin He, Yili Wang, Wenqi Fan, Xu Shen, Xin Juan, Rui Miao, Xin Wang

Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of over-smoothing as the model depth increases, which causes all node representations to converge to a single value and become indistinguishable. This issue stems from the inherent limitations of GNNs, which struggle to distinguish the importance of information from different neighborhoods. In this paper, we introduce MbaGCN, a novel graph convolutional architecture that draws inspiration from the Mamba paradigm-originally designed for sequence modeling. MbaGCN presents a new backbone for GNNs, consisting of three key components: the Message Aggregation Layer, the Selective State Space Transition Layer, and the Node State Prediction Layer. These components work in tandem to adaptively aggregate neighborhood information, providing greater flexibility and scalability for deep GNN models. While MbaGCN may not consistently outperform all existing methods on each dataset, it provides a foundational framework that demonstrates the effective integration of the Mamba paradigm into graph representation learning. Through extensive experiments on benchmark datasets, we demonstrate that MbaGCN paves the way for future advancements in graph neural network research.

📄 PDF Abstract BibTeX arXiv:2501.15461

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network Graph Representation LearningMambaNode Classification Representation Learning

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling

2025-11-10 · Xin He, Yili Wang, Yiwei Dai, Xin Wang arxiv

Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to become indistinguishable. While existing solutions, such as residual conn…

Representation Learning

Graph Partner Neural Networks for Semi-Supervised Learning on Graphs

2021-10-18 · Langzhang Liang, Cuiyun Gao, Shiyi Chen, Shishi Duan 외

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification…

Classification Graph Classification Link Prediction Node Classification

VEM-GCN: Topology Optimization with Variational EM for Graph Convolutional Networks

2021-01-01 · Rui Yang, Wenrui Dai, Chenglin Li, Junni Zou 외

Over-smoothing has emerged as a severe problem for node classification with graph convolutional networks (GCNs). In the view of message passing, the over-smoothing issue is caused by the observed noisy graph topology tha…

Classification General Classification Node Classification Stochastic Block Model

SStaGCN: Simplified stacking based graph convolutional networks

2021-11-16 · Jia Cai, Zhilong Xiong, Shaogao Lv

Graph convolutional network (GCN) is a powerful model studied broadly in various graph structural data learning tasks. However, to mitigate the over-smoothing phenomenon, and deal with heterogeneous graph structural data…

ATNPA: A Unified View of Oversmoothing Alleviation in Graph Neural Networks

2024-05-02 · Yufei Jin, Xingquan Zhu

Oversmoothing is a commonly observed challenge in graph neural network (GNN) learning, where, as layers increase, embedding features learned from GNNs quickly become similar/indistinguishable, making them incapable of di…

Graph Neural Network Relation