{"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/diversifying-support-vector-machines-for","title":"Diversifying Support Vector Machines for Boosting using Kernel Perturbation: Applications to Class Imbalance and Small Disjuncts","arxiv_id":"1712.08493","date":"2017-12-22","proceeding":null,"authors":["Shounak Datta","Sayak Nag","Sankha Subhra Mullick","Swagatam Das"],"abstract":"The diversification (generating slightly varying separating discriminators)\nof Support Vector Machines (SVMs) for boosting has proven to be a challenge due\nto the strong learning nature of SVMs. Based on the insight that perturbing the\nSVM kernel may help in diversifying SVMs, we propose two kernel perturbation\nbased boosting schemes where the kernel is modified in each round so as to\nincrease the resolution of the kernel-induced Reimannian metric in the vicinity\nof the datapoints misclassified in the previous round. We propose a method for\nidentifying the disjuncts in a dataset, dispelling the dependence on rule-based\nlearning methods for identifying the disjuncts. We also present a new\nperformance measure called Geometric Small Disjunct Index (GSDI) to quantify\nthe performance on small disjuncts for balanced as well as class imbalanced\ndatasets. Experimental comparison with a variety of state-of-the-art algorithms\nis carried out using the best classifiers of each type selected by a new\napproach inspired by multi-criteria decision making. The proposed method is\nfound to outperform the contending state-of-the-art methods on different\ndatasets (ranging from mildly imbalanced to highly imbalanced and characterized\nby varying number of disjuncts) in terms of three different performance indices\n(including the proposed GSDI).","url_abs":"http://arxiv.org/abs/1712.08493v1","url_pdf":"http://arxiv.org/pdf/1712.08493v1.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":"diversifying-support-vector-machines-for","repo_url":"https://github.com/Shounak-D/Kernel-Perturbation-based-Boosting-of-SVMs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}