Parameter Transfer Extreme Learning Machine based on Projective Model

TL;DR

This paper introduces a novel parameter transfer method for extreme learning machines using a projective model and structured sparsity, improving domain adaptation performance.

Contribution

It proposes a new transfer learning approach with a projective model and joint optimization, enhancing feature selection and transfer efficiency in ELMs.

Findings

Significantly outperforms non-transfer ELMs

Achieves better domain adaptation results

Effectively incorporates structured sparsity

Abstract

Recent years, transfer learning has attracted much attention in the community of machine learning. In this paper, we mainly focus on the tasks of parameter transfer under the framework of extreme learning machine (ELM). Unlike the existing parameter transfer approaches, which incorporate the source model information into the target by regularizing the di erence between the source and target domain parameters, an intuitively appealing projective-model is proposed to bridge the source and target model parameters. Specifically, we formulate the parameter transfer in the ELM networks by the means of parameter projection, and train the model by optimizing the projection matrix and classifier parameters jointly. Further more, the `L2,1-norm structured sparsity penalty is imposed on the source domain parameters, which encourages the joint feature selection and parameter transfer. To evaluate the e ectiveness of the proposed method, comprehensive experiments on several commonly used domain adaptation datasets are presented. The results show that the proposed method significantly outperforms the non-transfer ELM networks and other classical transfer learning methods.