Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

Nassif Roula; Vlaski Stefan; Richard Cedric; Chen Jie; Sayed Ali H.

首页> 外文期刊>IEEE Signal Processing Magazine >Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

【24h】

Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

机译：多任务在图表上学习：分布式，流式流机学习方法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

The problem of simultaneously learning several related tasks has received considerable attention in several domains, especially in machine learning, with the so-called multitask learning (MTL) problem, or learning to learn problem [1], [2]. MTL is an approach to inductive transfer learning (using what is learned for one problem to assist with another problem), and it helps improve generalization performance relative to learning each task separately by using the domain information contained in the training signals of related tasks as an inductive bias. Several strategies have been derived within this community under the assumption that all data are available beforehand at a fusion center.

机译：同时学习多个相关任务的问题在多个域中获得了相当大的关注，特别是在机器学习中，所谓的多任务学习（MTL）问题，或学习学习问题[1]，[2]。 MTL是一种归纳转移学习的方法（使用一个问题来帮助解决另一个问题的方法），并且它通过使用相关任务的训练信号中包含的域信息分开地，改善相对于学习每个任务的泛化性能。归纳偏见。在该社区中，在该社区中派生了几种策略，假设所有数据都在融合中心上市。

著录项

来源
《IEEE Signal Processing Magazine》 |2020年第3期|14-25|共12页
作者
Nassif Roula; Vlaski Stefan; Richard Cedric; Chen Jie; Sayed Ali H.;
展开▼
作者单位

Amer Univ Beirut AUB Beirut Lebanon|Ecole Polytech Fed Lausanne Adapt Syst Lab Lausanne Switzerland;

Ecole Polytech Fed Lausanne Adapt Syst Lab Lausanne Switzerland;

Univ Cote Azur Nice France|Inst Univ France Paris France|IEEE Signal Proc Soc SPS Reg 8 Europe Middle East Africa Piscataway NJ USA|French Fed CNRS Res Assoc Informat Signal Image Vis Paris France;

Univ Nice Sophia Antipolis Lagrange Lab Nice France|Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA|Northwestern Polytech Univ Xian Shaanxi Peoples R China;

Ecole Polytech Fed Lausanne Engn Lausanne Switzerland|Univ Calif Los Angeles Elect Engn Los Angeles CA 90024 USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Scaling-Up Distributed Processing of Data Streams for Machine Learning [J] . Nokleby Matthew, Raja Haroon, Bajwa Waheed U. Proceedings of the IEEE . 2020,第11期

机译：用于机器学习的数据流的缩放分布式处理
2. Classifying Uncertain and Evolving Data Streams with Distributed Extreme Learning Machine [J] . 韩东红, 张昕, 王国仁计算机科学技术学报（英文版） . 2015,第004期

机译：使用分布式极限学习机对不确定和不断发展的数据流进行分类
3. Research on Asynchronous Distributed Deep Learning Technology―Optimizing Machine Learning Models in the Age of Distributed Data Storage [J] . Kenta Niwa NTT Technical Review . 2021,第9期

机译：分布式数据存储时代异步分布式深度学习技术优化机器学习模型研究
4. Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network [C] . Pedro Avelar, Henrique Lemos, Marcelo Prates, International conference on artificial neural networks . 2019

机译：图神经网络上的多任务学习：使用统一网络学习多个图中心性度量
5. Aprendizaje maquina multitarea mediante edicion de datos y algoritmos de aprendizaje extremo. multitask learning with data editing and extreme learning machine. [D] . Bueno Crespo, Andres. 2013

机译：通过数据编辑和极限学习算法进行多任务机器学习。具有数据编辑和极限学习机的多任务学习。
6. Multitask feature learning approach for knowledge graph enhanced recommendations with RippleNet [O] . YueQun Wang, LiYan Dong, YongLi Li, 2021

机译：多任务特征学习方法用于知识图表增强了RIPPlenet的建议
7. Multitask fMRI and machine learning approach improve prediction of differential brain activity pattern in patients with insomnia disorder [O] . Mi Hyun Lee, Nambeom Kim, Jaeeun Yoo, 2021

机译：多任务FMRI和机器学习方法改进失眠症患者差异脑活动模式的预测

Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

摘要

著录项

相似文献

相关主题

期刊订阅