Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
8-2021
Abstract
In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a geometrically rich and diverse SPD neural architecture search space for an efficient SPD cell design. Further, we model our new NAS problem with a one-shot training process of a single supernet. Based on the supernet modeling, we exploit a differentiable NAS algorithm on our relaxed continuous search space for SPD neural architecture search. Statistical evaluation of our method on drone, action, and emotion recognition tasks mostly provides better results than the state-of-the-art SPD networks and traditional NAS algorithms. Empirical results show that our algorithm excels in discovering better performing SPD network design and provides models that are more than three times lighter than searched by the state-of-the-art NAS algorithms.
Discipline
OS and Networks | Systems Architecture
Research Areas
Data Science and Engineering
Publication
Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), Montreal, 2021 Aug 19-26
First Page
3002
Last Page
3009
Publisher
AAAI Press
City or Country
Virtual
Citation
SUKTHANKER, R.S.; HUANG, Zhiwu; KUMAR, S.; ENDSJO, E. G.; WU, Y.; and VAN, Gool L..
Neural architecture search of SPD manifold networks. (2021). Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), Montreal, 2021 Aug 19-26. 3002-3009.
Available at: https://ink.library.smu.edu.sg/sis_research/6410
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.