Have Graph -- Will Lift? The Case for Higher-Order Benchmarks

Bastian Rieck

cs.LGMay 8, 2026

Have Graph -- Will Lift? The Case for Higher-Order Benchmarks

Authors: Bastian Rieck

Organizations: AIDOS Lab, University of Fribourg, Switzerland · Institute of AI for Health, Helmholtz Munich, Germany

Abstract

After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of geometric deep learning, and paradigms that were once considered to be firmly in the realm of the abstract-like sheaves-have been "tamed" to serve as novel inductive biases for model architectures in topological deep learning. The veritable diversity of models, however, is in stark contrast to the scarcity of suitable benchmark datasets. As a result, researchers often resort to lifting existing graph datasets to include higher-order information. In this opinion paper, I want to encourage the community to also source new datasets, which may be used to prop up the foundations of our research field.

Explore similar work

No Triangulation Without Representation: Generalization in Topological Deep Learning
May 7, 2026Johannes S. Schmidt, Martin Carrasco, Ernst Röell +3Topological Deep Learning Triangulations
Differentiable Lifting for Topological Neural Networks
Aug 2, 2026Jorge Luiz Franco, Gabriel Duarte, Alexander Nikitin +3Topological Deep Learning Graph Neural Networks
TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning
Jul 30, 2026Brendan Kennedy, Tegan Emerson, Gregory Roek +2Pytorch Topological Data Analysis

May 7, 2026 · cs.LGJ/K move · Enter open · S save

No Triangulation Without Representation: Generalization in Topological Deep Learning

Johannes S. Schmidt, Martin Carrasco, Ernst Röell, Guy Wolf+2

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.

Topological Deep Learning Triangulations Deep Learning

Open paper Ask about it PDF

Abstract

Explore similar work

No Triangulation Without Representation: Generalization in Topological Deep Learning

Differentiable Lifting for Topological Neural Networks

TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning