EUVIMEDEUVIMED entdecken
Crossref

Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search

Chao Wang, Licheng Jiao, Jiaxuan Zhao, Lingling Li, Xu Liu, Fang Liu, Shuyuan Yang

IEEE Transactions on Evolutionary Computation · 2024-02 · 28 (1) · 208-222

DOI: 10.1109/tevc.2023.3255263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2024-02. Verfasst von Chao Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: Key Scientific Technological Innovation Research Project by Ministry of Education, National Natural Science Foundation of China Innovation Research Group Foundation, State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The construction of machine learning models involves many bi-level multiobjective optimization problems (BL-MOPs), where upper-level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of subproblems and the complex dependency across UL solutions and LL weights, a UL solution is feasible if and only if the LL weight is Pareto optimal. It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution. This article proposes a bi-level multiobjective learning framework (BLMOL), coupling the above decision-making process with the optimization process of the upper-level MOP (UL-MOP) by introducing LL preference $\boldsymbol {r}$ . Specifically, the UL variable and $\boldsymbol {r}$ are simultaneously searched to minimize multiple UL objectives by evolutionary multiobjective algorithms. The LL weight with respect to $\boldsymbol {r}$ is trained to minimize multiple LL objectives via gradient-based preference multiobjective algorithms. In addition, the preference surrogate model is constructed to replace the expensive evaluation process of the UL-MOP. We consider a novel case study on multitask graph neural topology search. It aims to find a set of Pareto topologies and their Pareto weights, representing different tradeoffs across tasks at UL and LL, respectively. The found graph neural network is employed to solve multiple tasks simultaneously, including graph classification, node classification, and link prediction. Experimental results demonstrate that BLMOL can outperform some state-of-the-art algorithms and generate well-representative UL solutions and LL weights.

Förderung

  • Key Scientific Technological Innovation Research Project by Ministry of Education
  • National Natural Science Foundation of China Innovation Research Group Foundation
  • State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China
  • Major Research Plan of the National Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Higher Education Discipline Innovation Project
  • Program for Cheung Kong Scholars and Innovative Research Team in University
  • ST Innovation Project from the Chinese Ministry of Education

Zitieren

APA

Wang, C., Jiao, L., Zhao, J., Li, L., Liu, X., Liu, F., & Yang, S. (2024). Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search. IEEE Transactions on Evolutionary Computation, 28(1), 208-222. https://doi.org/10.1109/tevc.2023.3255263

Vancouver

Wang C, Jiao L, Zhao J, Li L, Liu X, Liu F, et al. Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search. IEEE Transactions on Evolutionary Computation. 2024;28(1):208-222. doi:10.1109/tevc.2023.3255263

BibTeX
@article{Wang2024,
  author = {Wang, Chao and Jiao, Licheng and Zhao, Jiaxuan and Li, Lingling and Liu, Xu and Liu, Fang and Yang, Shuyuan},
  title = {Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search},
  journal = {IEEE Transactions on Evolutionary Computation},
  year = {2024},
  volume = {28},
  number = {1},
  pages = {208--222},
  doi = {10.1109/tevc.2023.3255263}
}
Kostenlos starten →