No Triangulation Without Representation: Generalization in Topological Deep Learning

• URL: http://arxiv.org/abs/2605.06467v1
• Date: Thu, 07 May 2026 15:55:24 GMT
• Title: No Triangulation Without Representation: Generalization in Topological Deep Learning
• Abstract summary: We show that both graph neural networks (GNNs) and higher-order message passing (HOMP) methods can saturate the benchmark.<n>Surprisingly, we find no indication that existing models are capable of generalizing beyond the structure of the data.
• Score: 21.366284585034474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite an ever-increasing interest in topological deep learning models that target higher-order datasets, there is no consensus on how to evaluate such models. This is exacerbated by the fact that topological objects permit operations, such as structural refinements, that are not appropriate for graph data. In this work, we extend MANTRA, a benchmark dataset containing manifold triangulations, to a larger class of manifolds with more diverse homeomorphism types. We show that, unlike prior claims, both graph neural networks (GNNs) and higher-order message passing (HOMP) methods can saturate the benchmark. However, we find that this is contingent on the right representation and feature assignment, emphasizing their importance in baseline models. We thus provide a novel evaluation protocol based on representational diversity and triangulation refinement. Surprisingly, we find no indication that existing models are capable of generalizing beyond the combinatorial structure of the data. This points towards a research gap in developing models that understand topological structure independent of scale. Our work thus provides the necessary scaffolding to evaluate future models and enable the development of topology-aware inductive biases.

Related papers

• SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D [51.32219731589742]
  3D scene graphs provide a structured representation of object entities and their relationships.<n>Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs)<n>In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model)
  arXiv  Detail & Related papers  (2026-03-04T21:19:54Z)
• Extracting Complex Topology from Multivariate Functional Approximation: Contours, Jacobi Sets, and Ridge-Valley Graphs [4.426174973462758]
  Implicit continuous models offer new perspectives on the storage, transfer, and analysis of scientific data.<n>We introduce the first framework to directly extract complex topological features from a type of continuous implicit model.<n>Our work is easily generalizable to any continuous implicit model that supports the queries of function values and high-order derivatives.
  arXiv  Detail & Related papers  (2025-08-11T05:41:24Z)
• Dissecting embedding method: learning higher-order structures from data [0.0]
  Geometric deep learning methods for data learning often include set of assumptions on the geometry of the feature space. These assumptions together with data being discrete and finite can cause some generalisations, which are likely to create wrong interpretations of the data and models outputs.
  arXiv  Detail & Related papers  (2024-10-14T08:19:39Z)
• MANTRA: The Manifold Triangulations Assemblage [33.363632055740254]
  We introduce MANTRA, the first large-scale, diverse, and intrinsically higher-order dataset for benchmarking higher-order models.<n>We demonstrate that while simplicial complex-based neural networks generally outperform their graph-based counterparts in capturing simple topological invariants.
  arXiv  Detail & Related papers  (2024-10-03T11:13:55Z)
• (Deep) Generative Geodesics [57.635187092922976]
  We introduce a newian metric to assess the similarity between any two data points. Our metric leads to the conceptual definition of generative distances and generative geodesics. Their approximations are proven to converge to their true values under mild conditions.
  arXiv  Detail & Related papers  (2024-07-15T21:14:02Z)
• LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering [59.89626219328127]
  Graph clustering is a fundamental problem in machine learning. Deep learning methods achieve the state-of-the-art results in recent years, but they still cannot work without predefined cluster numbers. We propose to address this problem from a fresh perspective of graph information theory.
  arXiv  Detail & Related papers  (2024-05-20T05:46:41Z)
• I Don't Need $\mathbf{u}$: Identifiable Non-Linear ICA Without Side Information [13.936583337756883]
  We introduce a new approach for identifiable non-linear ICA models. In particular, we focus on generative models which perform clustering in their latent space.
  arXiv  Detail & Related papers  (2021-06-09T17:22:08Z)
• Atlas Generative Models and Geodesic Interpolation [0.20305676256390928]
  We define the general class of Atlas Generative Models (AGMs), models with hybrid discrete-continuous latent space. We exemplify this by generalizing an algorithm for graph based geodesic to the setting of AGMs, and verify its performance experimentally.
  arXiv  Detail & Related papers  (2021-01-30T16:35:25Z)
• Mix Dimension in Poincar\'{e} Geometry for 3D Skeleton-based Action Recognition [57.98278794950759]
  Graph Convolutional Networks (GCNs) have already demonstrated their powerful ability to model the irregular data. We present a novel spatial-temporal GCN architecture which is defined via the Poincar'e geometry. We evaluate our method on two current largest scale 3D datasets.
  arXiv  Detail & Related papers  (2020-07-30T18:23:18Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)
• Interpretable Learning-to-Rank with Generalized Additive Models [78.42800966500374]
  Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models. We lay the groundwork for intrinsically interpretable learning-to-rank by introducing generalized additive models (GAMs) into ranking tasks.
  arXiv  Detail & Related papers  (2020-05-06T01:51:30Z)

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.