A Multi-objective Perspective Towards Improving Meta-Generalization

Weiduo Liao1,2; Ying Wei3; Qirui Sun1; Qingfu Zhang1; Hisao Ishibuchi2

10.1109/IJCNN60899.2024.10651555

2024-07-05

2161-4393

979-8-3503-5932-9

2024 International Joint Conference on Neural Networks (IJCNN)

30 June-5 July 2024

Yokohama, Japan

To improve meta-generalization, i.e., accommodating out-of-domain meta-testing tasks beyond meta-training ones, is of significance to extending the success of meta-learning beyond standard benchmarks. Previous heterogeneous meta-learning algorithms have shown that tailoring the global meta-knowledge by the learned clusters during meta-training promotes better meta-generalization to novel meta-testing tasks. Inspired by this, we propose a novel multi-objective perspective to sharpen the compositionality of the meta-trained clusters, through which we have empirically validated that the meta-generalization further improves. Grounded on the hierarchically structured meta-learning framework, we formulate a hypervolume loss to evaluate the degree of conflict between multiple cluster-conditioned parameters in the two-dimensional loss space over two randomly chosen tasks belonging to two clusters and two mixed tasks imitating out-of-domain tasks. Experimental results on more than 16 few-shot image classification datasets show not only improved performance on out-of-domain meta-testing datasets but also better clusters in visualization.

其他

1.Department of Computer Science, City University of Hong Kong
2.Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Southern University of Science and Technology
3.School of Computer Science and Engineering, Nanyang Technological University

Weiduo Liao,Ying Wei,Qirui Sun,et al. A Multi-objective Perspective Towards Improving Meta-Generalization[C],2024.