您现在的位置:首页>新闻中心>科研动态

科研动态

【医学部学术讲座】——Distributed Multi-task Relationship Learning分布式多任务关系学习

文章来源: 作者: 发布时间:2018年06月01日 点击数: 字体:

主讲嘉宾: Sinno Jialin Pan, 潘嘉林

Assistant Professor

Deputy Director of Data Science and AI Research Centre (DSAIR)

School of Computer Science and Engineering, Nanyang Technological University, Singapore

 

时间:     2018年06月05日上午 10:30 – 11:30

地点:     深圳大学西丽校区A2-517

主持人:   张治国 教授

 

报告内容简介:

Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of different tasks may be geo-distributed over different local machines. Due to heavy communication caused by transmitting the data and the issue of data privacy and security, it is impossible to send data of different task to a master machine to perform multi-task learning. Therefore, we offer a distributed multi-task learning framework that simultaneously learns predictive models for each task as well as task relationships between tasks alternatingly in the parameter server paradigm. In our framework, we first derive a general dual form for a family of regularized multi-task relationship learning methods. Subsequently, we propose a communication-efficient primal-dual distributed optimization algorithm to solve the dual problem by carefully designing local sub-problems to make the dual problem decomposable. Moreover, we provide a theoretical convergence analysis for the proposed algorithm, which is specific for distributed multi-task relationship learning. We conduct extensive experiments on both synthetic and real-world datasets to evaluate our proposed framework in terms of effectiveness and convergence.

 

报告嘉宾简介:

Dr Sinno Jialin Pan is a Nanyang Assistant Professor (university named assistant professorship) at the School of Computer Science and Engineering at Nanyang Technological University (NTU), Singapore. Prior to joining NTU, he was a scientist and Lab Head of text analytics with the Data Analytics Department, Institute for Infocomm Research, A*STAR, Singapore. He received his Ph.D. degree in computer science from the Hong Kong University of Science and Technology (HKUST) in 2011. His research interests include transfer learning, and its real-world applications. Recently, he was named in in IEEE’s biennial “AI’s 10 to Watch” for his contributions to transfer learning.

潘嘉林现为新加坡南洋理工大学计算机科学与工程学院南洋助理教授(大学冠名教授),数据科学与人工智能中心执行主任。他于2011年于香港科技大学获得博士学位,导师为杨强。他的研究兴趣是迁移学习及其实际应用,其迁移学习文章单篇被引用超过4000次。最近,他因其在迁移学习方面的贡献被选为IEEE 2018年度的“AI’s 10 to Watch”。

【打印文章】 【添加收藏】