TopoEmbedX: A General Framework for Representation Learning on Topological Domains

arXiv:2609.37884v1 Announce Type: new Abstract: Topological structures such as simplicial complexes, hypergraphs, and cell complexes extend standard graph models by modeling higher-order relationships. These structures appear in many modern datasets and require specialized methods for generating meaningful embeddings. In this paper, we introduce TopoEmbedX, a unified framework for embedding a wide range of topological domains into Euclidean spaces. The package brings together several existing topological embedding algorithms---DeepCell, Cell2Vec, CellDiff2Vec, HOLE, and HOGLEE---and introduces five new algorithms: ComplexNetMF, ComplexRep, ComplexRandNE, ComplexWalklets, and ComplexHeat. These algorithms extend well-known graph embedding techniques to higher-order settings using the augmented Hasse graph of a topological domain. TopoEmbedX provides a clear, consistent, and easy-to-use framework for topological representation learning. Experiments show that the embeddings generated by TopoEmbedX support tasks such as classification and regression across multidimensional data.

Related

• Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning
• Scaling Higher-Order Graph Learning with Maximal Clique Complexes
• TopoFormer: Topology Meets Attention for Graph Learning
• Direct Topology Tracking in Continuous Implicit Models
• Topology-induced Operators Reveal Complementary Graph Representations without Training

Source: arXiv cs.LG | 2026-09-30