HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices
Abstract
Currently, prominent Transformer architectures applied on graphs and meshes for shape analysis tasks employ traditional attention layers that heavily utilize spectral features requiring costly eigenvalue decomposition-based methods. To encode the mesh structure, these methods derive positional embeddings, that heavily rely on eigenvalue decomposition based operations, e.g. on the Laplacian matrix, or on heat-kernel signatures, which are then concatenated to the input features. This paper proposes a novel approach inspired by the explicit construction of the Hodge Laplacian operator in Discrete Exterior Calculus as a product of discrete Hodge operators and exterior derivatives, i.e. . We adjust the Transformer architecture in a novel deep learning layer that utilizes the multi-head attention mechanism to approximate Hodge matrices , and and learn families of discrete operators that act on mesh vertices, edges and faces. Our approach results in a computationally-efficient architecture that achieves comparable performance in mesh segmentation and classification tasks, through a direct learning framework, while eliminating the need for costly eigenvalue decomposition operations or complex preprocessing operations.
Cite
@article{arxiv.2509.01839,
title = {HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices},
author = {Akis Nousias and Stavros Nousias},
journal= {arXiv preprint arXiv:2509.01839},
year = {2025}
}
Comments
15 pages, 13 figures, 10 tables