基于自步学习策略的归纳式迁移学习模型研究  

Research on Inductive Transfer Learning Model Based on Self-paced Learning Strategy

作　　者：张宇[1] 刘波[2] Zhang Yu;Liu Bo(School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China;School of Automation,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学计算机学院,广东广州510006 [2]广东工业大学自动化学院,广东广州510006

出　　处：《广东工业大学学报》2023年第4期31-36,共6页Journal of Guangdong University of Technology

基　　金：国家自然科学基金资助项目(61876044,62076074)。

摘　　要：在机器学习任务中很多时候是单任务学习,所以往往会忽略学习任务之间的相关性,并且在单任务学习中容易忽略样本的复杂度,为此,本文提出了一种新的基于自步学习策略的归纳式迁移学习模型,通过对当前多个相关的源任务共享参数学习构建一个预测模型,从而解决目标任务的分类问题。首先提出模型基于自步学习的策略,按照预先设定的自步学习模型参数对多个相关的源任务进行联合学习,利用源任务中样本的损失大小与难易程度对学习的样本赋予一个权重,在迭代的过程中更新自步学习的参数从而挑选出比较合适的样本(损失较小的样本),然后使用在多个相关的源任务中学习到的知识帮助学习目标任务,构建多个相关迁移学习目标任务的模型,将多个源任务学习到的模型迁移到相关的目标任务中从而提高模型的泛化能力,最后通过拉格朗日函数进一步优化目标模型以提高分类器的性能。实验结果表明,提出的模型在相同的实验条件下优于现有的归纳式迁移学习模型。Machine learning tasks are usually single-task learning.However,in practical applications,the learning tasks are often related.As a result,the correlation between tasks is often ignored,and the complexity of samples is sometimes not considered in single-task learning.To address this,this paper proposes a new inductive transfer learning model based on the self-paced learning strategyby constructing a prediction model to learn the shared parameters of multiple related source tasks.First,the proposed model uses the strategy of self-paced learning to jointly learns the multiple related source tasks,and weights the learning samples according to the loss and difficulty degree of the samples in the source tasks.The parameters of the self-paced learning are iteratively updated to select the optimal samples with the less loss.Then,the knowledge learned from multiple related source tasks guide the learning of target tasks to construct multiple models for related transfer learning target tasks,and transfer these models to related target tasks to improve their generalization ability.Finally,we optimize the target model by using the Lagrange function to improve the performance of the classifiers.Experimental results show that the proposed model is superior to the existing transfer learning model under the same experimental conditions.

关 键 词：自步学习 归纳式迁移学习 支持向量机 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]