{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/parameter-transfer-extreme-learning-machine","title":"Parameter Transfer Extreme Learning Machine based on Projective Model","arxiv_id":"1809.01018","date":"2018-09-04","proceeding":null,"authors":["Chao Chen","Boyuan Jiang","Xinyu Jin"],"abstract":"Recent years, transfer learning has attracted much attention in the community\nof machine learning. In this paper, we mainly focus on the tasks of parameter\ntransfer under the framework of extreme learning machine (ELM). Unlike the\nexisting parameter transfer approaches, which incorporate the source model\ninformation into the target by regularizing the di erence between the source\nand target domain parameters, an intuitively appealing projective-model is\nproposed to bridge the source and target model parameters. Specifically, we\nformulate the parameter transfer in the ELM networks by the means of parameter\nprojection, and train the model by optimizing the projection matrix and\nclassifier parameters jointly. Further more, the `L2,1-norm structured sparsity\npenalty is imposed on the source domain parameters, which encourages the joint\nfeature selection and parameter transfer. To evaluate the e ectiveness of the\nproposed method, comprehensive experiments on several commonly used domain\nadaptation datasets are presented. The results show that the proposed method\nsignificantly outperforms the non-transfer ELM networks and other classical\ntransfer learning methods.","url_abs":"http://arxiv.org/abs/1809.01018v2","url_pdf":"http://arxiv.org/pdf/1809.01018v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"parameter-transfer-extreme-learning-machine","repo_url":"https://github.com/BoyuanJiang/PTELM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}