Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework

• URL: http://arxiv.org/abs/2505.21251v2
• Date: Wed, 28 May 2025 13:03:58 GMT
• Title: Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
• Authors: Mustafa Hajij, Lennart Bastian, Sarah Osentoski, Hardik Kabaria, John L. Davenport, Sheik Dawood, Balaji Cherukuri, Joseph G. Kocheemoolayil, Nastaran Shahmansouri, Adrian Lew, Theodore Papamarkou, Tolga Birdal,
• Abstract summary: We introduce copresheaf topological neural networks (CTNNs), a powerful and unifying framework that encapsulates a wide spectrum of deep learning architectures.<n>CTNNs address the principled design of neural architectures tailored to specific tasks and data types.<n>Our empirical results on structured data benchmarks demonstrate that CTNNs consistently outperform conventional baselines.
• Score: 10.470880055362406
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce copresheaf topological neural networks (CTNNs), a powerful and unifying framework that encapsulates a wide spectrum of deep learning architectures, designed to operate on structured data: including images, point clouds, graphs, meshes, and topological manifolds. While deep learning has profoundly impacted domains ranging from digital assistants to autonomous systems, the principled design of neural architectures tailored to specific tasks and data types remains one of the field's most persistent open challenges. CTNNs address this gap by grounding model design in the language of copresheaves, a concept from algebraic topology that generalizes and subsumes most practical deep learning models in use today. This abstract yet constructive formulation yields a rich design space from which theoretically sound and practically effective solutions can be derived to tackle core challenges in representation learning: long-range dependencies, oversmoothing, heterophily, and non-Euclidean domains. Our empirical results on structured data benchmarks demonstrate that CTNNs consistently outperform conventional baselines, particularly in tasks requiring hierarchical or localized sensitivity. These results underscore CTNNs as a principled, multi-scale foundation for the next generation of deep learning architectures.

Related papers

• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Towards characterizing the value of edge embeddings in Graph Neural Networks [47.01312576529216]
  Graph neural networks (GNNs) are the dominant approach to solving machine learning problems defined over graphs. We consider the benefits of architectures that maintain and update edge embeddings.
  arXiv  Detail & Related papers  (2024-10-13T15:03:24Z)
• Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse [14.817633094318253]
  We study how architectural choices and structure of the data effect gradient rank bounds in deep neural networks (DNNs) Our theoretical analysis provides these bounds for training fully-connected, recurrent, and convolutional neural networks. We also demonstrate, both theoretically and empirically, how design choices like activation function linearity, bottleneck layer introduction, convolutional stride, and sequence truncation influence these bounds.
  arXiv  Detail & Related papers  (2024-02-09T19:28:02Z)
• Homological Convolutional Neural Networks [4.615338063719135]
  We propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models.
  arXiv  Detail & Related papers  (2023-08-26T08:48:51Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• Homological Neural Networks: A Sparse Architecture for Multivariate Complexity [0.0]
  We develop a novel deep neural network unit characterized by a sparse higher-order graphical architecture built over the homological structure of underlying data. Results demonstrate the advantages of this novel design which can tie or overcome the results of state-of-the-art machine learning and deep learning models using only a fraction of parameters.
  arXiv  Detail & Related papers  (2023-06-27T09:46:16Z)
• Deep neural networks architectures from the perspective of manifold learning [0.0]
  This paper is a comprehensive comparison and description of neural network architectures in terms of ge-ometry and topology. We focus on the internal representation of neural networks and on the dynamics of changes in the topology and geometry of a data manifold on different layers.
  arXiv  Detail & Related papers  (2023-06-06T04:57:39Z)
• The Neural Race Reduction: Dynamics of Abstraction in Gated Networks [12.130628846129973]
  We introduce the Gated Deep Linear Network framework that schematizes how pathways of information flow impact learning dynamics. We derive an exact reduction and, for certain cases, exact solutions to the dynamics of learning. Our work gives rise to general hypotheses relating neural architecture to learning and provides a mathematical approach towards understanding the design of more complex architectures.
  arXiv  Detail & Related papers  (2022-07-21T12:01:03Z)
• Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks [61.17075071853949]
  Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory.
  arXiv  Detail & Related papers  (2021-07-21T17:34:33Z)
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges [50.22269760171131]
  The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. This text is concerned with exposing pre-defined regularities through unified geometric principles. It provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers.
  arXiv  Detail & Related papers  (2021-04-27T21:09:51Z)
• Model-Based Machine Learning for Communications [110.47840878388453]
  We review existing strategies for combining model-based algorithms and machine learning from a high level perspective. We focus on symbol detection, which is one of the fundamental tasks of communication receivers.
  arXiv  Detail & Related papers  (2021-01-12T19:55:34Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Understanding Deep Architectures with Reasoning Layer [60.90906477693774]
  We show that properties of the algorithm layers, such as convergence, stability, and sensitivity, are intimately related to the approximation and generalization abilities of the end-to-end model. Our theory can provide useful guidelines for designing deep architectures with reasoning layers.
  arXiv  Detail & Related papers  (2020-06-24T00:26:35Z)

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.