← Search

Manuel Lecha

2 accepted papers

2026

Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding

ICLR 2026poster

Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses this limitation by leveraging combinatorial topological spaces, such as simplicial or cell complexes. However, existing TDL…

Cited by 0SourcecodeScholar
2025

Higher-Order Topological Directionality and Directed Simplicial Neural Networks

ICASSP 2025accepted

Topological Deep Learning (TDL) has emerged as a paradigm to process and learn from signals defined on higher-order combinatorial topological spaces, such as simplicial or cell complexes. Although many complex systems have an asymmetric relational structure, most TDL models forcibly symmetrize these…

Cited by 0SourceScholar