基于分类误差一致性准则的自适应知识迁移

Adaptive Knowledge Transfer Based on Classification-error Consensus Regularization

目前大多数迁移学习方法在利用源域数据辅助目标域数据建模时,通常假设源域中的数据均与目标域数据相关。然而在实际应用中,源域中的数据并非都与目标域数据的相关程度一致,若基于上述假设往往会导致负迁移效应。为此,该文首先提出分类误差一致性准则(CCR),对源域与目标域分类误差的概率分布积分平方误差进行最小化度量。此外,该文提出一种基于CCR的自适应知识迁移学习方法(CATL),该方法可以快速地从源域中自动确定出与目标域相关的数据及其权重,以辅助目标域模型的构建,使其能在提高知识迁移效率的同时缓解负迁移学习效应。在真实图像以及文本数据集上的实验结果验证了CATL方法的优势。

Most current transfer learning methods are modeled by utilizing the source data with the assumption that all data in the source domain are equally related to the target domain.In many practical applications,however,this assumption may induce negative learning effect when it becomes invalid.To tackle this issue,by minimizing the integrated squared error of the probability distribution of the source and target domain classification errors,the Classification-error Consensus Regularization(CCR)is proposed.Furthermore,CCRbased Adaptive knowledge Transfer Learning(CATL)method is developed to quickly determine the correlative source data and the corresponding weights.The proposed method can alleviate the negative transfer learning effect while improving the efficiency of knowledge transfer.The experimental results on the real image and text datasets validate the advantages of the CATL method.