.png){kind=icon}
返回
Multi-objective dynamic distribution adaptation with instance reweighting for transfer feature learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2023.110303.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In knowledge adaptation, the source and target knowledge are transferred into the same mapping space by simultaneously reducing the difference between the marginal and conditional distributions; however, it is difficult to precisely balance the two distributions at each transformation. To address this problem, a novel multi-objective dynamic distribution adaptation (MODDA) with instance reweighting is proposed to reduce discrepancies between the two distributions. In addition, a customised non-dominated sorting genetic algorithm-II (NSGA2) optimisation method is presented for searching the optimal cumulative weight path, and four genetic operator combinations are compared to determine which one is optimal for MODDA. Moreover, kernel mean matching is proposed for the first time for dynamic compensation based on an individual's relevance in instance reweighting. The experimental results confirm that MODDA outperforms other state-of-the-art algorithms in terms of the classification accuracy for 16 well-known cross-domain tasks.(c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Domain adaptation
Multi-objective evolutionary algorithm
Instance reweighting
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
Autologous graft-versus-host disease: harnessing anti-tumor immunity through impaired self-tolerance
PREAI
分享收藏Multivariate Functional Principal Component Analysis for Data Observed on Different (Dimensional) Domains在不同 (维) 域上观察到的数据的多元功能主成分分析
OAAI
OAAI分享收藏
查看更多内容