Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

• URL: http://arxiv.org/abs/2605.10975v1
• Date: Fri, 08 May 2026 22:35:17 GMT
• Title: Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
• Abstract summary: Hierarchical Multi-view HAAR (HMH) is a novel graph-learning framework that scales in near-linear time.<n>HMH outperforms state-of-the-art spectral baselines, achieving up to a 3% improvement on node classification and 7% points on graph classification datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However, existing spectral Graph Neural Network (GNN) approaches tailored for heterophilous graph classification suffer from hub-dominated (node with large degree) aggregation and oversmoothing, as their suboptimal polynomial filters introduce approximation errors and blend distant signals. To address the degree-biased aggregation and suboptimal polynomial filtering, we introduce a Hierarchical Multi-view HAAR (HMH), a novel spectral graph-learning framework that scales in near-linear time . HMH first learns feature- and structure-aware signed affinities via a heterophily-aware encoder, then constructs a soft graph hierarchy guided by these embeddings. At each hierarchical level, HMH constructs a sparse, orthonormal, and locality-aware Haar basis to apply learnable spectral filters in the frequency domain. Finally, skip-connection unpooling layers combine outputs from all hierarchical levels back into the original graph, effectively preventing hub domination and long-range signal bottleneck (over-squashing). Experimentation shows that HMH outperforms state-of-the-art spectral baselines, achieving up to a 3% improvement on node classification and 7% points on graph classification datasets, all while maintaining linear scalability.

Related papers

• Spectro-Riemannian Graph Neural Networks [39.901731107377095]
  Cusp Laplacian is an extension of the traditional graph Laplacian based on Ollivier-Ricci curvature.<n>Cusp Pooling is a hierarchical attention mechanism combined with a curvature-based positional encoding.
  arXiv  Detail & Related papers  (2025-02-01T11:31:01Z)
• GSpect: Spectral Filtering for Cross-Scale Graph Classification [9.800723513820046]
  We propose GSpect, an advanced spectral graph filtering model for cross-scale graph classification tasks. On open data sets, GSpect improves the performance of classification accuracy by 1.62% on average, and for a maximum of 3.33% on PROTEINS. GSpect fills the gap in cross-scale graph classification studies and has potential to provide assistance in application research like diagnosis of brain disease.
  arXiv  Detail & Related papers  (2024-08-31T03:26:32Z)
• Graph Contrastive Learning under Heterophily via Graph Filters [51.46061703680498]
  Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. In this work, we propose an effective graph CL method, namely HLCL, for learning graph representations under heterophily. Our extensive experiments show that HLCL outperforms state-of-the-art graph CL methods on benchmark datasets with heterophily, as well as large-scale real-world graphs, by up to 7%, and outperforms graph supervised learning methods on datasets with heterophily by up to 10%.
  arXiv  Detail & Related papers  (2023-03-11T08:32:39Z)
• Incorporating Heterophily into Graph Neural Networks for Graph Classification [6.709862924279403]
  Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily. We develop a novel GNN architecture called IHGNN (short for Incorporating Heterophily into Graph Neural Networks) We empirically validate IHGNN on various graph datasets and demonstrate that it outperforms the state-of-the-art GNNs for graph classification.
  arXiv  Detail & Related papers  (2022-03-15T06:48:35Z)
• Quasi-Framelets: Robust Graph Neural Networks via Adaptive Framelet Convolution [28.474359021962346]
  We propose a multiscale framelet convolution for spectral graph neural networks (GNNs) The proposed design excels in filtering out unwanted spectral information and significantly reduces the adverse effects of noisy graph signals. It exhibits remarkable resilience to noisy data and adversarial attacks, highlighting its potential as a robust solution for real-world graph applications.
  arXiv  Detail & Related papers  (2022-01-11T00:10:28Z)
• Improving Spectral Graph Convolution for Learning Graph-level Representation [27.76697047602983]
  We show that for learning representations of the entire graphs, the topological distance seems necessary since it characterizes the basic relations between nodes. By removing it, as well as the limitation of graph filters, the resulting new architecture significantly boosts performance on learning graph representations. It serves as an understanding that quantitatively measures the effects of the spectrum to input signals in comparison to the well-known spectral/low-pass filters.
  arXiv  Detail & Related papers  (2021-12-14T04:50:46Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification [50.899576891296235]
  Convolutional neural networks have been widely applied to hyperspectral image classification. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
  arXiv  Detail & Related papers  (2021-06-26T06:24:51Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks [67.25782890241496]
  We propose a higher-order Attribute-Enhancing Graph Neural Network (HAEGNN) for heterogeneous network representation learning. HAEGNN simultaneously incorporates meta-paths and meta-graphs for rich, heterogeneous semantics. It shows superior performance against the state-of-the-art methods in node classification, node clustering, and visualization.
  arXiv  Detail & Related papers  (2021-04-16T04:56:38Z)
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs [6.018995094882323]
  Graph neural networks (GNNs) have been extensively studied for prediction tasks on graphs. Most GNNs assume local homophily, i.e., strong similarities in localneighborhoods. We propose a flexible GNN model, which is capable of handling any graphs without beingrestricted by their underlying homophily.
  arXiv  Detail & Related papers  (2021-03-26T00:35:36Z)
• Graph Cross Networks with Vertex Infomax Pooling [69.38969610952927]
  We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.
  arXiv  Detail & Related papers  (2020-10-05T06:34:23Z)

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.