Simplicial Complex Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-01 · 46 (1) · 561-575
DOI: 10.1109/tpami.2023.3323624 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-01. Verfasst von Hanrui Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Talent Support Project of Guangzhou Association for Science and Technology, Guangzhou Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
Graph-structured data, where nodes exhibit either pair-wise or high-order relations, are ubiquitous and essential in graph learning. Despite the great achievement made by existing graph learning models, these models use the direct information (edges or hyperedges) from graphs and do not adopt the underlying indirect information (hidden pair-wise or high-order relations). To address this issue, in this paper, we propose a general framework named Simplicial Complex Neural (SCN) network, in which we construct a simplicial complex based on the direct and indirect graph information from a graph so that all information can be employed in the complex network learning. Specifically, we learn representations of simplices by aggregating and integrating information from all the simplices together via layer-by-layer simplicial complex propagation. In consequence, the representations of nodes, edges, and other high-order simplices are obtained simultaneously and can be used for learning purposes. By making use of block matrix properties, we derive the theoretical bound of the simplicial complex filter learnt by the propagation and establish the generalization error bound of the proposed simplicial complex network. We perform extensive experiments on node (0-simplex), edge (1-simplex), and triangle (2-simplex) classifications, and promising results demonstrate the performance of the proposed method is better than that of existing graph and hypergraph network approaches.
Förderung
- National Natural Science Foundation of China
- Young Talent Support Project of Guangzhou Association for Science and Technology
- Guangzhou Basic and Applied Basic Research Foundation
- China Postdoctoral Science Foundation
- Guangdong Natural Science Foundation of China
- Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization
- Science and Technology Planning Project of Guangdong Province
- Fundamental Research Funds for Central Universities
Zitieren
APA
Wu, H., Yip, A., Long, J., Zhang, J., & Ng, M. K. (2024). Simplicial Complex Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(1), 561-575. https://doi.org/10.1109/tpami.2023.3323624
Vancouver
Wu H, Yip A, Long J, Zhang J, Ng MK. Simplicial Complex Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(1):561-575. doi:10.1109/tpami.2023.3323624
BibTeX
@article{Wu2024,
author = {Wu, Hanrui and Yip, Andy and Long, Jinyi and Zhang, Jia and Ng, Michael K},
title = {Simplicial Complex Neural Networks},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {1},
pages = {561--575},
doi = {10.1109/tpami.2023.3323624}
}
EUVIMED