所属单位：

International Joint Conferences on Artificial Intelligence

发表刊物：

IJCAI International Joint Conference on Artificial Intelligence, Volume 2023-August

摘要：

This paper studies multiparty learning, aiming to learn a model using the private data of different participants. Model reuse is a promising solution for multiparty learning, assuming that a local model has been trained for each party. Considering the potential sample selection bias among different parties, some heterogeneous model reuse approaches have been developed. However, although pre-trained local classifiers are utilized in these approaches, the characteristics of the local data are not well exploited. This motivates us to estimate the density of local data and design an auxiliary model together with the local classifiers for reuse. To address the scenarios where some local models are not well pre-trained, we further design a multiparty cross-entropy loss for calibration. Upon existing works, we address a challenging problem of heterogeneous model reuse from a decision theory perspective and take advantage of recent advances in density estimation. Experimental results on both synthetic and benchmark data demonstrate the superiority of the proposed method.

合写作者：

Luo Yong,Hu Han,He Fengxiang,Du Bo,Chen Yixin,Tao Dacheng

第一作者：

Tang Anke

论文类型：

文章

通讯作者：

Su Kehua

文献类型：

J

页面范围：

4244-4252

ISSN号：

1045-0823

是否译文：

否

发表时间：

2023-08-01

收录刊物：

EI