Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering

Author:

de Freitas Joao Machado1,Berg Sebastian2,Geiger Bernhard C.1,Mucke Manfred2

Affiliation:

1. Know-Center GmbH,Graz,Austria

2. Materials Center Leoben Forschung GmbH,Leoben,Austria

Publisher

IEEE

Reference27 articles.

1. Deep variational information bottleneck;alemi;Proc Int Conf on Learning Representations (ICLR),0

2. Multi-task learning using uncer-tainty to weigh losses for scene geometry and semantics;kendall;Proc IEEE Conf on Computer Vision and Pattern Recognition (CVPR),0

3. Compression-Based Regularization With an Application to Multitask Learning

4. Which tasks should be learned together in multi-task learning?;standley;Proceedings of the 37th International Conference on Machine Learning ser Proceedings of Machine Learning Research,0

5. Learning task grouping and overlap in multi-task learning;kumar;Proc Int Conf on Machine Learning (ICML),0

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection;2023 International Joint Conference on Neural Networks (IJCNN);2023-06-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3