Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells

• URL: http://arxiv.org/abs/2604.17548v1
• Date: Sun, 19 Apr 2026 17:22:38 GMT
• Title: Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells
• Abstract summary: Persistent homology (PH) encodes global information, such as cycles, and is thus increasingly integrated into graph neural networks (GNNs)<n>We analyze contractions as a principled topological operation, in particular, for graph representation learning.<n>We introduce Hourglass Persistence, a class of topological descriptors that interleave a sequence of inclusions and contractions to boost expressivity, learnability, and stability.
• Score: 25.74211632462519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Persistent homology (PH) encodes global information, such as cycles, and is thus increasingly integrated into graph neural networks (GNNs). PH methods in GNNs typically traverse an increasing sequence of subgraphs. In this work, we first expose limitations of this inclusion procedure. To remedy these shortcomings, we analyze contractions as a principled topological operation, in particular, for graph representation learning. We study the persistence of contraction sequences, which we call Contraction Homology (CH). We establish that forward PH and CH differ in expressivity. We then introduce Hourglass Persistence, a class of topological descriptors that interleave a sequence of inclusions and contractions to boost expressivity, learnability, and stability. We also study related families parametrized by two paradigms. We also discuss how our framework extends to simplicial and cellular networks. We further design efficient algorithms that are pluggable into end-to-end differentiable GNN pipelines, enabling consistent empirical improvements over many PH methods across standard real-world graph datasets. Code is available at \href{https://github.com/Aalto-QuML/Hourglass}{this https URL}.

Related papers

• Can we ease the Injectivity Bottleneck on Lorentzian Manifolds for Graph Neural Networks? [0.0]
  Lorentzian Graph Isomorphic Network (LGIN) is a novel HGNN designed for enhanced discrimination within the Lorentzian model.<n>LGIN is the first to adapt principles of powerful, highly discriminative GNN architectures to a Riemannian manifold.
  arXiv  Detail & Related papers  (2025-03-31T18:49:34Z)
• Boosting Graph Pooling with Persistent Homology [8.477383770884508]
  naively plugging PH features into GNN layers always results in marginal improvement with low interpretability. We investigate a novel mechanism for injecting global topological invariance into pooling layers using PH, motivated by the observation that filtration operation in PH naturally aligns graph pooling in a cut-off manner. Experimentally, we apply our mechanism to a collection of graph pooling methods and observe consistent and substantial performance gain over several popular datasets.
  arXiv  Detail & Related papers  (2024-02-26T07:00:24Z)
• Revealing Decurve Flows for Generalized Graph Propagation [108.80758541147418]
  This study addresses the limitations of the traditional analysis of message-passing, central to graph learning, by defining em textbfgeneralized propagation with directed and weighted graphs. We include a preliminary exploration of learned propagation patterns in datasets, a first in the field.
  arXiv  Detail & Related papers  (2024-02-13T14:13:17Z)
• Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks [23.61142321685077]
  Graph convolution networks (GCNs) are extensively utilized in various graph tasks to mine knowledge from spatial data. Our study marks the pioneering attempt to quantitatively investigate the GCN robustness over omnipresent heterophilic graphs for node classification. We present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs.
  arXiv  Detail & Related papers  (2023-12-27T05:35:14Z)
• Going beyond persistent homology using persistent homology [5.724311218570011]
  We introduce a novel concept of color-separating sets to provide a complete resolution to this important problem. We propose RePHINE for learning topological features on graphs.
  arXiv  Detail & Related papers  (2023-11-10T16:12:35Z)
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes [4.23480641508611]
  Graph Neural Networks (GNNs) are theoretically bounded by the 1-Weisfeiler-Lehman test. Our study presents a novel perspective by focusing on simple paths within graphs during the topological message-passing process.
  arXiv  Detail & Related papers  (2023-08-13T19:45:20Z)
• Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions [51.597480162777074]
  Graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions. Recent works point out that different graph learning tasks require different ranges of interactions between nodes. We study two common graph construction methods in scientific domains, i.e., emphK-nearest neighbor (KNN) graphs and emphfully-connected (FC) graphs.
  arXiv  Detail & Related papers  (2022-05-15T11:38:14Z)
• 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)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)

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.