{"ID":2876119,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.01839","arxiv_id":"2509.01839","title":"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. $(L := \\star_0^{-1} d_0^T \\star_1 d_0)$. We adjust the Transformer architecture in a novel deep learning layer that utilizes the multi-head attention mechanism to approximate Hodge matrices $\\star_0$, $\\star_1$ and $\\star_2$ and learn families of discrete operators $L$ 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.","short_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...","url_abs":"https://arxiv.org/abs/2509.01839","url_pdf":"https://arxiv.org/pdf/2509.01839v5","authors":"[\"Akis Nousias\",\"Stavros Nousias\"]","published":"2025-09-01T23:43:43Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}