Briola, Antonio;
Wang, Yuanrong;
Bartolucci, Silvia;
Aste, Tomaso;
(2024)
Homological Convolutional Neural Networks.
In: Sanborn, Sophia and Shewmake, Christian and Azeglio, Simone and Miolane, Nina, (eds.)
Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations.
(pp. pp. 206-231).
PMLR: Proceedings of Machine Learning Research: New Orleans, Lousiana, USA.
Preview |
Text
Bartolucci_briola24a.pdf Download (1MB) | Preview |
Abstract
Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with classic machine learning approaches being often computationally cheaper and equally effective than increasingly complex deep learning architectures. The challenge arises from the fact that, in tabular data, the correlation among features is weaker than the one from spatial or semantic relationships in images or natural language, and the dependency structures need to be modeled without any prior information. In this work, we propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations to gain relational information from sparse tabular inputs. The resulting model leverages the power of convolution and is centered on a limited number of concepts from network topology to guarantee: (i) a data-centric and deterministic building pipeline; (ii) a high level of interpretability over the inference process; and (iii) an adequate room for scalability. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models, demonstrating that our approach reaches state-of-the-art performances on these challenging datasets. The code to reproduce all our experiments is provided at https://github.com/FinancialComputingUCL/HomologicalCNN.
| Type: | Proceedings paper |
|---|---|
| Title: | Homological Convolutional Neural Networks |
| Event: | 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations |
| Location: | New Orleans, Lousiana, USA |
| Dates: | 16 Dec 2023 - 16 Dec 2023 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v228/briola24a.html |
| Language: | English |
| Additional information: | This is an Open Access article published under a Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10218100 |
Archive Staff Only
 |
View Item |
