A Secure Federated Data-Driven Evolutionary Multi-objective Optimization Algorithm

Liu, Qiqi; Yan, Yongsheng; Ligeti, Péter; Jin, Yaochu

doi:10.48550/arxiv.2210.08295

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This makes BLMOL perform poorly for BL-MOPs which own an insufficient evaluation budget or a large UL search space. In the future, we plan to extend the BLMOL framework to more BL-MOPs in machine learning, such as feature selection [43], [44], federated learning [46], [84], and fair learning [85], [86]. In these paradigms, there often exist multiple objectives that need to be optimized simultaneously.…”

Section: Discussionmentioning

confidence: 99%

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

Wang

Jiao

Zhao

et al. 2024

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

The construction of machine learning models involves many bi-level multi-objective 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 sub-problems and the complex dependency across UL solutions and LL weights, an 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 paper proposes a bi-level multi-objective learning framework (BLMOL), coupling the above decisionmaking process with the optimization process of the UL-MOP by introducing LL preference r. Specifically, the UL variable and r are simultaneously searched to minimize multiple UL objectives by evolutionary multi-objective algorithms. The LL weight with respect to r is trained to minimize multiple LL objectives via gradient-based preference multi-objective 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 multi-task graph neural topology search. It aims to find a set of Pareto topologies and their Pareto weights, representing different trade-offs 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.

show abstract