{"title":"Multi-Label Multi-Task Learning with Dynamic Task Weight Balancing","authors":"Tianyi Wang, Shu‐Ching Chen","doi":"10.1109/IRI49571.2020.00042","DOIUrl":null,"url":null,"abstract":"Data collected from real-world environments often contain multiple objects, scenes, and activities. In comparison to single-label problems, where each data sample only defines one concept, multi-label problems allow the co-existence of multiple concepts. To exploit the rich semantic information in real-world data, multi-label classification has seen many applications in a variety of domains. The traditional approaches to multi-label problems tend to have the side effects of increased memory usage, slow model inference speed, and most importantly the under-utilization of the dependency across concepts. In this paper, we adopt multi-task learning to address these challenges. Multi-task learning treats the learning of each concept as a separate job, while at the same time leverages the shared representations among all tasks. We also propose a dynamic task balancing method to automatically adjust the task weight distribution by taking both sample-level and task-level learning complexities into consideration. Our framework is evaluated on a disaster video dataset and the performance is compared with several state-of-the-art multi-label and multi-task learning techniques. The results demonstrate the effectiveness and supremacy of our approach.","PeriodicalId":93159,"journal":{"name":"2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science : IRI 2020 : proceedings : virtual conference, 11-13 August 2020. IEEE International Conference on Information Reuse and Integration (21st : 2...","volume":"61 1","pages":"245-252"},"PeriodicalIF":0.0000,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science : IRI 2020 : proceedings : virtual conference, 11-13 August 2020. IEEE International Conference on Information Reuse and Integration (21st : 2...","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRI49571.2020.00042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Data collected from real-world environments often contain multiple objects, scenes, and activities. In comparison to single-label problems, where each data sample only defines one concept, multi-label problems allow the co-existence of multiple concepts. To exploit the rich semantic information in real-world data, multi-label classification has seen many applications in a variety of domains. The traditional approaches to multi-label problems tend to have the side effects of increased memory usage, slow model inference speed, and most importantly the under-utilization of the dependency across concepts. In this paper, we adopt multi-task learning to address these challenges. Multi-task learning treats the learning of each concept as a separate job, while at the same time leverages the shared representations among all tasks. We also propose a dynamic task balancing method to automatically adjust the task weight distribution by taking both sample-level and task-level learning complexities into consideration. Our framework is evaluated on a disaster video dataset and the performance is compared with several state-of-the-art multi-label and multi-task learning techniques. The results demonstrate the effectiveness and supremacy of our approach.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于动态任务权重平衡的多标签多任务学习
从现实环境中收集的数据通常包含多个对象、场景和活动。与单标签问题(每个数据样本只定义一个概念)相比,多标签问题允许多个概念共存。为了挖掘真实数据中丰富的语义信息,多标签分类在各个领域得到了广泛的应用。处理多标签问题的传统方法往往具有内存使用量增加、模型推理速度慢以及最重要的是概念间依赖关系利用率不足等副作用。在本文中,我们采用多任务学习来解决这些挑战。多任务学习将每个概念的学习视为一项独立的工作,同时利用所有任务之间的共享表征。我们还提出了一种动态任务平衡方法,通过同时考虑样本级和任务级学习复杂性来自动调整任务权分布。我们的框架在灾难视频数据集上进行了评估,并与几种最先进的多标签和多任务学习技术进行了性能比较。结果证明了我们的方法的有效性和优越性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Synthetic CT Generation. Natural Language-based Integration of Online Review Datasets for Identification of Sex Trafficking Businesses. An Adaptive and Dynamic Biosensor Epidemic Model for COVID-19 Relating the Empirical Foundations of Attack Generation and Vulnerability Discovery Latent Feature Modelling for Recommender Systems
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1