Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.05558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917888140509184 |
|---|---|
| author | Piperno, Simone Battiloro, Claudio Ceschini, Andrea Dominici, Francesca Di Lorenzo, Paolo Panella, Massimo |
| author_facet | Piperno, Simone Battiloro, Claudio Ceschini, Andrea Dominici, Francesca Di Lorenzo, Paolo Panella, Massimo |
| contents | Graph Neural Networks (GNNs) excel at learning from graph-structured data but are limited to modeling pairwise interactions, insufficient for capturing higher-order relationships present in many real-world systems. Topological Deep Learning (TDL) has allowed for systematic modeling of hierarchical higher-order interactions by relying on combinatorial topological spaces such as simplicial complexes. In parallel, Quantum Neural Networks (QNNs) have been introduced to leverage quantum mechanics for enhanced computational and learning power. In this work, we present the first Quantum Topological Deep Learning Model: Quantum Simplicial Networks (QSNs), being QNNs operating on simplicial complexes. QSNs are a stack of Quantum Simplicial Layers, which are inspired by the Ising model to encode higher-order structures into quantum states. Experiments on synthetic classification tasks show that QSNs can outperform classical simplicial TDL models in accuracy and efficiency, demonstrating the potential of combining quantum computing with TDL for processing data on combinatorial topological spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Simplicial Neural Networks Piperno, Simone Battiloro, Claudio Ceschini, Andrea Dominici, Francesca Di Lorenzo, Paolo Panella, Massimo Neural and Evolutionary Computing Graph Neural Networks (GNNs) excel at learning from graph-structured data but are limited to modeling pairwise interactions, insufficient for capturing higher-order relationships present in many real-world systems. Topological Deep Learning (TDL) has allowed for systematic modeling of hierarchical higher-order interactions by relying on combinatorial topological spaces such as simplicial complexes. In parallel, Quantum Neural Networks (QNNs) have been introduced to leverage quantum mechanics for enhanced computational and learning power. In this work, we present the first Quantum Topological Deep Learning Model: Quantum Simplicial Networks (QSNs), being QNNs operating on simplicial complexes. QSNs are a stack of Quantum Simplicial Layers, which are inspired by the Ising model to encode higher-order structures into quantum states. Experiments on synthetic classification tasks show that QSNs can outperform classical simplicial TDL models in accuracy and efficiency, demonstrating the potential of combining quantum computing with TDL for processing data on combinatorial topological spaces. |
| title | Quantum Simplicial Neural Networks |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2501.05558 |