Hierarchical Pooling for Sheaf Neural Networks

• URL: http://arxiv.org/abs/2606.20932v1
• Date: Thu, 18 Jun 2026 20:50:27 GMT
• Title: Hierarchical Pooling for Sheaf Neural Networks
• Abstract summary: We introduce Hierarchical Sheaf Pool (HiSP), a sheaf-aware pooling framework based on local spectral coarsening.<n>HiSP constructs each coarse stalk by projecting fine stalk-valued features onto the low-frequency eigenmodes of the cluster-internal sheaf Laplacian.<n>We analyze the approximation induced by coarsening by separating truncation loss, due to discarded local modes, from realization loss due to representing the projected operator as coarse sheaf.
• Score: 20.79323358337401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibility across edges. Unlike standard graph diffusion, which encourages neighboring node features to become similar, sheaf diffusion promotes consistency through the restriction maps and can therefore model more general relationships between neighboring nodes. However, existing sheaf neural architectures mainly operate at a fixed graph resolution and do not provide a principled pooling mechanism for building hierarchical representations. In this paper, we introduce Hierarchical Sheaf Pool (HiSP), a sheaf-aware pooling framework based on local spectral coarsening. Given a partition of the graph, HiSP constructs each coarse stalk by projecting fine stalk-valued features onto the low-frequency eigenmodes of the cluster-internal sheaf Laplacian. These local modes define a cochain-level prolongation map, which allows the fine sheaf energy to be represented on the coarse space through a Galerkin operator. We further analyze the approximation induced by coarsening by separating truncation loss, due to discarded local modes, from realization loss, due to representing the projected operator as a coarse sheaf. Finally, we implement HiSP as a GNN pooling layer compatible with SNNs and provide a PyG implementation supporting batching, lifted sheaf Laplacians, and hierarchical architectures.

Related papers

• Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs [81.39865232674413]
  Graph Neural Networks (GNNs) have emerged as a powerful tool for wireless resource allocation.<n>This work establishes theoretical results for transferability of GNNs over graphs derived from sparse Random Geometric Graphs (RGGs)
  arXiv  Detail & Related papers  (2026-06-02T15:42:14Z)
• Layer Embedding Deep Fusion Graph Neural Network [25.30982656886312]
  Graph Neural Networks (GNNs) have demonstrated impressive performance in learning representations from graph-structured data.<n>We propose a novel framework named Layer Embedding Deep Fusion Graph Neural Network (LEDF-GNN)
  arXiv  Detail & Related papers  (2026-04-25T14:25:02Z)
• Graph Signal Diffusion Models for Wireless Resource Allocation [74.84410305593006]
  We consider constrained ergodic resource optimization in wireless networks with graph-structured interference.<n>We show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates.
  arXiv  Detail & Related papers  (2026-04-06T21:12:25Z)
• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization [13.021238902084647]
  Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features.<n>We introduce SGPC (Sheaf GNNs with PAC-Bayes), a unified architecture that combines cellular-sheaf message passing with several mechanisms.<n> Experiments on nine homophilic and heterophilic benchmarks show that SGPC outperforms state-of-the-art spectral and sheaf-based GNNs.
  arXiv  Detail & Related papers  (2025-08-01T06:39:28Z)
• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions [64.17845687013434]
  We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
  arXiv  Detail & Related papers  (2025-07-19T04:46:53Z)
• A Spectral Interpretation of Redundancy in a Graph Reservoir [51.40366905583043]
  This work revisits the definition of the reservoir in the Multiresolution Reservoir Graph Neural Network (MRGNN)<n>It proposes a variant based on a Fairing algorithm originally introduced in the field of surface design in computer graphics.<n>The core contribution of the paper lies in the theoretical analysis of the algorithm from a random walks perspective.
  arXiv  Detail & Related papers  (2025-07-17T10:02:57Z)
• ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networks [19.889547537748395]
  Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from the node representations. We propose a new hierarchical pooling operation, namely the Edge-Node Attention-based Differentiable Pooling (ENADPool)
  arXiv  Detail & Related papers  (2024-05-16T16:08:49Z)
• MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy [27.328628715885287]
  A graph neural network (GNN) architecture is capable of modeling data with cross-instance relations.<n>An important subclass of this architecture involves layers designed such that the forward pass iteratively reduces a graph-regularized energy function of interest.<n>We propose a sampling-based energy function and scalable GNN layers that iteratively reduce it, guided by convergence guarantees in certain settings.<n>We also instantiate a full GNN architecture based on these designs, and the model achieves competitive accuracy and scalability when applied to the largest publicly-available node classification benchmark exceeding 1TB in size.
  arXiv  Detail & Related papers  (2023-10-19T04:30:14Z)
• Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals [7.6435511285856865]
  Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. locality assumption of GNNs hampers their ability to capture long-range dependencies and global patterns in graphs. We propose a new inductive bias based on variational analysis, drawing inspiration from the Brachchronistoe problem.
  arXiv  Detail & Related papers  (2023-07-01T04:44:43Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)

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.