Multi-Objective Meta Learning

Ye，Feiyang1,2; Lin，Baijiong1; Yue，Zhixiong1,2; Guo，Pengxin1; Xiao，Qiao3; Zhang，Yu1,4

2021

1049-5258

Advances in Neural Information Processing Systems

26

21338-21351

Meta learning with multiple objectives has been attracted much attention recently since many applications need to consider multiple factors when designing learning models. Existing gradient-based works on meta learning with multiple objectives mainly combine multiple objectives into a single objective in a weighted sum manner. This simple strategy usually works but it requires to tune the weights associated with all the objectives, which could be time consuming. Different from those works, in this paper, we propose a gradient-based Multi-Objective Meta Learning (MOML) framework without manually tuning weights. Specifically, MOML formulates the objective function of meta learning with multiple objectives as a Multi-Objective Bi-Level optimization Problem (MOBLP) where the upper-level subproblem is to solve several possibly conflicting objectives for the meta learner. To solve the MOBLP, we devise the first gradient-based optimization algorithm by alternatively solving the lower-level and upper-level subproblems via the gradient descent method and the gradient-based multi-objective optimization method, respectively. Theoretically, we prove the convergence properties of the proposed gradient-based optimization algorithm. Empirically, we show the effectiveness of the proposed MOML framework in several meta learning problems, including few-shot learning, domain adaptation, multi-task learning, and neural architecture search. The source code of MOML is available at https://github.com/Baijiong-Lin/MOML.

第一 ; 通讯

英语

EI

National Natural Science Foundation of China[62076118];

20222412232710

Gradient methods ; Learning systems

Optimization Techniques:921.5 ; Numerical Methods:921.6

2-s2.0-85124639579

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,China
2.University of Technology Sydney,Australia
3.Eindhoven University of Technology,Netherlands
4.Peng Cheng Laboratory,China

Ye，Feiyang,Lin，Baijiong,Yue，Zhixiong,et al. Multi-Objective Meta Learning[C],2021:21338-21351.