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

• URL: http://arxiv.org/abs/2511.06756v2
• Date: Wed, 12 Nov 2025 01:18:41 GMT
• Title: Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
• Authors: Xin He, Yili Wang, Yiwei Dai, Xin Wang,
• Abstract summary: We propose a Dual Mamba-enhanced Graph Convolutional Network (DMbaGCN) to address over-smoothing.<n>DMbaGCN consists of two modules: the Local State-Evolution Mamba (LSEMba) for local neighborhood aggregation, and the Global Context-Aware Mamba (GCAMba) that leverages Mamba's global attention capabilities to incorporate global context for each node.
• Score: 12.115520585626046
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 connections and skip layers, alleviate this issue to some extent, they fail to explicitly model how node representations evolve in a node-specific and progressive manner across layers. Moreover, these methods do not take global information into account, which is also crucial for mitigating the over-smoothing problem. To address the aforementioned issues, in this work, we propose a Dual Mamba-enhanced Graph Convolutional Network (DMbaGCN), which is a novel framework that integrates Mamba into GNNs to address over-smoothing from both local and global perspectives. DMbaGCN consists of two modules: the Local State-Evolution Mamba (LSEMba) for local neighborhood aggregation and utilizing Mamba's selective state space modeling to capture node-specific representation dynamics across layers, and the Global Context-Aware Mamba (GCAMba) that leverages Mamba's global attention capabilities to incorporate global context for each node. By combining these components, DMbaGCN enhances node discriminability in deep GNNs, thereby mitigating over-smoothing. Extensive experiments on multiple benchmarks demonstrate the effectiveness and efficiency of our method.

Related papers

• Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework [66.2103745798444]
  Saliency Mamba (Samba) is a pure Mamba-based architecture that flexibly handles various distinct salient object detection tasks.<n>Samba individually outperforms existing methods across six SOD tasks on 22 datasets with lower computational cost.<n>Samba+ achieves even superior results on these tasks and datasets by using a single trained versatile model.
  arXiv  Detail & Related papers  (2026-02-02T03:34:25Z)
• Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining [95.00432497331583]
  Multi-Prior Hierarchical Mamba (MPHM) network for image deraining.<n>MPHM integrates macro-semantic textual priors (CLIP) for task-level semantic guidance and micro-structural visual priors (DINOv2) for scene-aware structural information.<n>Experiments demonstrate MPHM's state-of-the-art performance, achieving a 0.57 dB PSNR gain on the Rain200H dataset.
  arXiv  Detail & Related papers  (2025-11-17T08:08:59Z)
• Prompt-Guided Dual-Path UNet with Mamba for Medical Image Segmentation [18.060052357308763]
  We propose a prompt-guided CNN-Mamba dual-path UNet, termed PGM-UNet, for medical image segmentation.<n>We introduce a prompt-guided residual Mamba module that adaptively extracts dynamic visual prompts from the original input data.<n>We also design a local-global information fusion network, comprising a local information extraction module, a prompt-guided residual Mamba module, and a multi-focus attention fusion module.
  arXiv  Detail & Related papers  (2025-03-25T12:12:07Z)
• Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space [33.677431350509224]
  We introduce MbaGCN, a novel graph convolutional architecture that draws inspiration from the Mamba paradigm.<n>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.
  arXiv  Detail & Related papers  (2025-01-26T09:09:44Z)
• LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba [54.85262314960038]
  Local Attentional Mamba blocks capture both global contexts and local details with linear complexity. Our model exhibits exceptional scalability and surpasses the performance of DiT across various model scales on ImageNet at 256x256 resolution. Compared to state-of-the-art diffusion models on ImageNet 256x256 and 512x512, our largest model presents notable advantages, such as a reduction of up to 62% GFLOPs.
  arXiv  Detail & Related papers  (2024-08-05T16:39:39Z)
• All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN [61.28174338723467]
  We propose a Node-Specific Layer Aggregation and filtration architecture, termed NoSAF, for Graph Neural Networks. NoSAF provides a reliable information filter for each layer's nodes to sieve out information beneficial for the subsequent layer. NoSAF also incorporates a compensation mechanism that replenishes information in every layer of the model, allowing NoSAF to perform meaningful computations even in very deep layers.
  arXiv  Detail & Related papers  (2024-05-13T16:27:12Z)
• MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs [1.7648680700685022]
  Underwater Image Enhancement (UIE) techniques aim to address the problem of underwater image degradation due to light absorption and scattering. Recent years, both Convolution Neural Network (CNN)-based and Transformer-based methods have been widely explored. MambaUIE is able to efficiently synthesize global and local information and maintains a very small number of parameters with high accuracy.
  arXiv  Detail & Related papers  (2024-04-22T05:12:11Z)
• DGMamba: Domain Generalization via Generalized State Space Model [80.82253601531164]
  Domain generalization(DG) aims at solving distribution shift problems in various scenes. Mamba, as an emerging state space model (SSM), possesses superior linear complexity and global receptive fields. We propose a novel framework for DG, named DGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-04-11T14:35:59Z)
• PointMamba: A Simple State Space Model for Point Cloud Analysis [65.59944745840866]
  We propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
  arXiv  Detail & Related papers  (2024-02-16T14:56:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.