探索基于原型的软标签数据蒸馏在不平衡数据分类中的潜力

Radu Rosu, Mihaela Breaban, H. Luchian
{"title":"探索基于原型的软标签数据蒸馏在不平衡数据分类中的潜力","authors":"Radu Rosu, Mihaela Breaban, H. Luchian","doi":"10.1109/SYNASC57785.2022.00034","DOIUrl":null,"url":null,"abstract":"Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire original dataset. Consequently, data distillation methods are usually tied to a specific ML algorithm. While recent literature deals mainly with distillation of large collections of images in the context of neural network models, tabular data distillation is much less represented and mainly focused on a theoretical perspective. The current paper explores the potential of a simple distillation technique previously proposed in the context of Less-than-one shot learning. The main goal is to push further the performance of prototype-based soft-labels distillation in terms of classification accuracy, by integrating optimization steps in the distillation process. The analysis is performed on real-world data sets with various degrees of imbalance. Experimental studies trace the capability of the method to distill the data, but also the opportunity to act as an augmentation method, i.e. to generate new data that is able to increase model accuracy when used in conjunction with - as opposed to instead of - the original data.","PeriodicalId":446065,"journal":{"name":"2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Exploring the potential of prototype-based soft-labels data distillation for imbalanced data classification\",\"authors\":\"Radu Rosu, Mihaela Breaban, H. Luchian\",\"doi\":\"10.1109/SYNASC57785.2022.00034\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire original dataset. Consequently, data distillation methods are usually tied to a specific ML algorithm. While recent literature deals mainly with distillation of large collections of images in the context of neural network models, tabular data distillation is much less represented and mainly focused on a theoretical perspective. The current paper explores the potential of a simple distillation technique previously proposed in the context of Less-than-one shot learning. The main goal is to push further the performance of prototype-based soft-labels distillation in terms of classification accuracy, by integrating optimization steps in the distillation process. The analysis is performed on real-world data sets with various degrees of imbalance. Experimental studies trace the capability of the method to distill the data, but also the opportunity to act as an augmentation method, i.e. to generate new data that is able to increase model accuracy when used in conjunction with - as opposed to instead of - the original data.\",\"PeriodicalId\":446065,\"journal\":{\"name\":\"2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SYNASC57785.2022.00034\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SYNASC57785.2022.00034","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

数据集蒸馏旨在通过少量人工生成的数据项合成数据集,当用作训练数据时,复制或近似机器学习(ML)模型,就好像它是在整个原始数据集上训练的一样。因此,数据蒸馏方法通常与特定的ML算法相关联。虽然最近的文献主要涉及神经网络模型背景下大量图像集合的蒸馏,但表格数据蒸馏的代表性要少得多,并且主要集中在理论视角上。当前的论文探索了一种简单的蒸馏技术的潜力,这种技术以前在少于一次学习的背景下提出。主要目标是通过整合蒸馏过程中的优化步骤,进一步提高基于原型的软标签蒸馏在分类精度方面的性能。该分析是在具有不同程度不平衡的真实数据集上进行的。实验研究追踪了该方法提取数据的能力,但也有机会作为一种增强方法,即生成新的数据,当与原始数据结合使用时,能够提高模型的准确性,而不是代替原始数据。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Exploring the potential of prototype-based soft-labels data distillation for imbalanced data classification
Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire original dataset. Consequently, data distillation methods are usually tied to a specific ML algorithm. While recent literature deals mainly with distillation of large collections of images in the context of neural network models, tabular data distillation is much less represented and mainly focused on a theoretical perspective. The current paper explores the potential of a simple distillation technique previously proposed in the context of Less-than-one shot learning. The main goal is to push further the performance of prototype-based soft-labels distillation in terms of classification accuracy, by integrating optimization steps in the distillation process. The analysis is performed on real-world data sets with various degrees of imbalance. Experimental studies trace the capability of the method to distill the data, but also the opportunity to act as an augmentation method, i.e. to generate new data that is able to increase model accuracy when used in conjunction with - as opposed to instead of - the original data.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信